< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 74 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.6029. Min Act: -0.0001

Data Index: 1505090 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.4293. Min Act: -0.0001

Data Index: 1499971 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.4130. Min Act: -0.0001

Data Index: 747785 (The Pile)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.4506. Min Act: -0.0001

Data Index: 231861 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.3141. Min Act: -0.0001

Data Index: 1439585 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.3065. Min Act: -0.0001

Data Index: 486808 (The Pile)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.2921. Min Act: -0.0001

Data Index: 1304679 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.1995. Min Act: -0.0001

Data Index: 648928 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.0477. Min Act: -0.0001

Data Index: 757977 (The Pile)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.0418. Min Act: -0.0001

Data Index: 53507 (The Pile)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.0349. Min Act: -0.0001

Data Index: 1628980 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6029. Min Range: -2.6029

Max Act: 1.9938. Min Act: -0.0001

Data Index: 1969666 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.0542. Min Act: -0.0001

Data Index: 777152 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.0971. Min Act: -0.0001

Data Index: 1363171 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.1341. Min Act: -0.0001

Data Index: 874156 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.0105. Min Act: -0.0001

Data Index: 1486914 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6029. Min Range: -2.6029

Max Act: 1.8116. Min Act: -0.0001

Data Index: 1028706 (The Pile)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6029. Min Range: -2.6029

Max Act: 1.9732. Min Act: -0.0001

Data Index: 1289327 (The Pile)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.0975. Min Act: -0.0001

Data Index: 307732 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6029. Min Range: -2.6029

Max Act: 1.8395. Min Act: -0.0001

Data Index: 1318661 (The Pile)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #19