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

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

Neuron 2878 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.8701. Min Act: -0.0000

Data Index: 396855 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.8600. Min Act: -0.0000

Data Index: 738368 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.9166. Min Act: -0.0001

Data Index: 874576 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.7098. Min Act: -0.0000

Data Index: 158483 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.6740. Min Act: -0.0000

Data Index: 1092474 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.7371. Min Act: -0.0001

Data Index: 554659 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.8294. Min Act: -0.0001

Data Index: 143082 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.7326. Min Act: -0.0001

Data Index: 1091208 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.6308. Min Act: -0.0001

Data Index: 602912 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.7143. Min Act: -0.0001

Data Index: 998999 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.7128. Min Act: -0.0000

Data Index: 1079570 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.6572. Min Act: -0.0001

Data Index: 8148 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.7306. Min Act: -0.0001

Data Index: 156047 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.6241. Min Act: -0.0000

Data Index: 1087074 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5333. Min Act: -0.0000

Data Index: 379313 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.6014. Min Act: -0.0000

Data Index: 1130347 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.6028. Min Act: -0.0001

Data Index: 264927 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.6783. Min Act: -0.0000

Data Index: 1079143 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5560. Min Act: -0.0001

Data Index: 705062 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5606. Min Act: -0.0000

Data Index: 519259 (C4 (Web Text))

Max Activating Token Index: 318