Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 335 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1326779 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0147. Min Act: -0.0006

Data Index: 308815 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0006

Data Index: 896334 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0151. Min Act: -0.0006

Data Index: 700349 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0136. Min Act: -0.0006

Data Index: 723618 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0151. Min Act: -0.0006

Data Index: 916850 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0141. Min Act: -0.0006

Data Index: 406397 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1537060 (Python Code)

Max Activating Token Index: 347

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0123. Min Act: -0.0006

Data Index: 449085 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0122. Min Act: -0.0006

Data Index: 646524 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0126. Min Act: -0.0006

Data Index: 964363 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0139. Min Act: -0.0006

Data Index: 576847 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1076605 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1031938 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0115. Min Act: -0.0006

Data Index: 694888 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0128. Min Act: -0.0005

Data Index: 86658 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0108. Min Act: -0.0006

Data Index: 425387 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0118. Min Act: -0.0006

Data Index: 787803 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0130. Min Act: -0.0006

Data Index: 906388 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0110. Min Act: -0.0006

Data Index: 502031 (C4 (Web Text))

Max Activating Token Index: 848