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

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

Neuron 924 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: 0.0120. Min Range: -0.0120

Max Act: 0.0120. Min Act: -0.0006

Data Index: 74163 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0105. Min Act: -0.0006

Data Index: 645833 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1333401 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1090337 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0102. Min Act: -0.0006

Data Index: 181732 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0100. Min Act: -0.0006

Data Index: 701735 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1016995 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0104. Min Act: -0.0006

Data Index: 105913 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0106. Min Act: -0.0006

Data Index: 730098 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0103. Min Act: -0.0006

Data Index: 371605 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0100. Min Act: -0.0006

Data Index: 250704 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0099. Min Act: -0.0006

Data Index: 830207 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0100. Min Act: -0.0006

Data Index: 300422 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0102. Min Act: -0.0006

Data Index: 467711 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0097. Min Act: -0.0006

Data Index: 454485 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1183157 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0096. Min Act: -0.0006

Data Index: 255560 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0098. Min Act: -0.0006

Data Index: 10412 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0103. Min Act: -0.0006

Data Index: 301898 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0098. Min Act: -0.0006

Data Index: 593831 (C4 (Web Text))

Max Activating Token Index: 257