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

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

Neuron 1400 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.5936. Min Act: -0.0000

Data Index: 329635 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1352904 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.5083. Min Act: -0.0000

Data Index: 599720 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4687. Min Act: -0.0000

Data Index: 534792 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4212. Min Act: -0.0000

Data Index: 377732 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1012452 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4182. Min Act: -0.0000

Data Index: 286644 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1031670 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4162. Min Act: -0.0000

Data Index: 371417 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4161. Min Act: -0.0000

Data Index: 207196 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4070. Min Act: -0.0000

Data Index: 994544 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4008. Min Act: -0.0000

Data Index: 935754 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3859. Min Act: -0.0000

Data Index: 692576 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3858. Min Act: -0.0000

Data Index: 640677 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4101. Min Act: -0.0000

Data Index: 430358 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.4096. Min Act: 0.0000

Data Index: 405234 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3870. Min Act: -0.0000

Data Index: 865356 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1015641 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3987. Min Act: -0.0000

Data Index: 479382 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.5936. Min Range: -0.5936

Max Act: 0.3828. Min Act: -0.0000

Data Index: 345981 (C4 (Web Text))

Max Activating Token Index: 20