Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3787 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.9186. Min Act: -0.0000

Data Index: 977564 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8107. Min Act: -0.0000

Data Index: 467566 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1812340 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1880055 (The Pile)

Max Activating Token Index: 72

Text #4

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8040. Min Act: -0.0000

Data Index: 64059 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7780. Min Act: -0.0000

Data Index: 340276 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1080591 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1710271 (The Pile)

Max Activating Token Index: 361

Text #8

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7134. Min Act: -0.0000

Data Index: 142823 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1929512 (The Pile)

Max Activating Token Index: 466

Text #10

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1669947 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7475. Min Act: -0.0000

Data Index: 431186 (The Pile)

Max Activating Token Index: 75

Text #12

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1408784 (The Pile)

Max Activating Token Index: 285

Text #13

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1281008 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1047465 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1738330 (The Pile)

Max Activating Token Index: 700

Text #16

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1376548 (The Pile)

Max Activating Token Index: 559

Text #17

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1201502 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6875. Min Act: -0.0000

Data Index: 157079 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1644161 (The Pile)

Max Activating Token Index: 300