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

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

Neuron 924 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1221. Min Act: -0.0000

Data Index: 405323 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1106. Min Act: -0.0000

Data Index: 321365 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1038. Min Act: -0.0001

Data Index: 320305 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1118. Min Act: -0.0000

Data Index: 449757 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1053. Min Act: -0.0000

Data Index: 117537 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0903. Min Act: -0.0000

Data Index: 471400 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1017. Min Act: -0.0000

Data Index: 131765 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0994. Min Act: -0.0000

Data Index: 422254 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1306464 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1159347 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0748. Min Act: -0.0001

Data Index: 276908 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1016943 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0903. Min Act: -0.0000

Data Index: 471006 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1004. Min Act: -0.0000

Data Index: 297203 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0884. Min Act: -0.0000

Data Index: 825093 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0917. Min Act: -0.0001

Data Index: 591865 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0878. Min Act: -0.0000

Data Index: 810664 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1116564 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0949. Min Act: -0.0000

Data Index: 838250 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0778. Min Act: -0.0000

Data Index: 79190 (C4 (Web Text))

Max Activating Token Index: 402