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

Dataset: The Pile

Neuron 3082 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.3186. Min Act: -0.0000

Data Index: 673495 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.1211. Min Act: -0.0000

Data Index: 477764 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.1367. Min Act: -0.0000

Data Index: 422845 (The Pile)

Max Activating Token Index: 202

Text #3

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.1661. Min Act: -0.0000

Data Index: 120977 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.1356. Min Act: -0.0000

Data Index: 1062278 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 1.3186. Min Range: -1.3186

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1147293 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1129299 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.1099. Min Act: -0.0000

Data Index: 1962455 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1482552 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.0464. Min Act: 0.0000

Data Index: 805247 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.0765. Min Act: -0.0000

Data Index: 912463 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 1.3186. Min Range: -1.3186

Max Act: 0.9680. Min Act: -0.0000

Data Index: 2361 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 1.3186. Min Range: -1.3186

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1920766 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 1.3186. Min Range: -1.3186

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1749535 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.0593. Min Act: -0.0000

Data Index: 540877 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 1.3186. Min Range: -1.3186

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1534218 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.0143. Min Act: -0.0000

Data Index: 147925 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.0033. Min Act: -0.0000

Data Index: 142953 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 1.3186. Min Range: -1.3186

Max Act: 1.0606. Min Act: -0.0000

Data Index: 1794295 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 1.3186. Min Range: -1.3186

Max Act: 0.9290. Min Act: -0.0000

Data Index: 339381 (The Pile)

Max Activating Token Index: 599