< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3013 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.9369. Min Act: -0.0001

Data Index: 1380605 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.8557. Min Act: -0.0001

Data Index: 288018 (The Pile)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7419. Min Act: -0.0001

Data Index: 1709023 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7557. Min Act: -0.0001

Data Index: 293147 (The Pile)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7354. Min Act: -0.0001

Data Index: 804247 (The Pile)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7053. Min Act: -0.0001

Data Index: 1751446 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7632. Min Act: -0.0001

Data Index: 1922290 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6309. Min Act: -0.0001

Data Index: 761104 (The Pile)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6685. Min Act: -0.0001

Data Index: 666168 (The Pile)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6918. Min Act: -0.0001

Data Index: 1602742 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1909089 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6828. Min Act: -0.0001

Data Index: 929671 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6768. Min Act: -0.0001

Data Index: 1252184 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6726. Min Act: -0.0001

Data Index: 688837 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6615. Min Act: -0.0001

Data Index: 1823691 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7142. Min Act: -0.0001

Data Index: 375376 (The Pile)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5745. Min Act: -0.0001

Data Index: 27741 (The Pile)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6451. Min Act: -0.0001

Data Index: 947261 (The Pile)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6414. Min Act: -0.0001

Data Index: 1089605 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6039. Min Act: -0.0001

Data Index: 1655110 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #19