< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 2023 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2947. Min Act: -0.0000

Data Index: 918581 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2660. Min Act: -0.0001

Data Index: 838341 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2787. Min Act: -0.0001

Data Index: 38388 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2590. Min Act: -0.0001

Data Index: 106002 (The Pile)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1494290 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2447. Min Act: -0.0001

Data Index: 962191 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2438. Min Act: -0.0001

Data Index: 530729 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2523. Min Act: -0.0001

Data Index: 1978958 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2486. Min Act: 0.0000

Data Index: 1539196 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2394. Min Act: -0.0001

Data Index: 902506 (The Pile)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2520. Min Act: -0.0001

Data Index: 120132 (The Pile)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2529. Min Act: -0.0001

Data Index: 652250 (The Pile)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2464. Min Act: -0.0001

Data Index: 609424 (The Pile)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2415. Min Act: -0.0000

Data Index: 695672 (The Pile)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2413. Min Act: -0.0001

Data Index: 448004 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1637364 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2390. Min Act: -0.0001

Data Index: 769384 (The Pile)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2285. Min Act: -0.0001

Data Index: 1780900 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2285. Min Act: -0.0001

Data Index: 362696 (The Pile)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2346. Min Act: -0.0001

Data Index: 1055974 (The Pile)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #19