Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1630 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1874. Min Range: -4.1874

Max Act: 4.1874. Min Act: -0.0000

Data Index: 122212 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 4.1874. Min Range: -4.1874

Max Act: 3.9168. Min Act: -0.0000

Data Index: 695780 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 4.1874. Min Range: -4.1874

Max Act: 3.0874. Min Act: -0.0000

Data Index: 283706 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 4.1874. Min Range: -4.1874

Max Act: 3.1215. Min Act: -0.0000

Data Index: 503671 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 4.1874. Min Range: -4.1874

Max Act: 3.3503. Min Act: -0.0000

Data Index: 788784 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 4.1874. Min Range: -4.1874

Max Act: 3.2224. Min Act: -0.0000

Data Index: 1089526 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 4.1874. Min Range: -4.1874

Max Act: 3.0270. Min Act: -0.0000

Data Index: 1208451 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.7493. Min Act: -0.0000

Data Index: 953071 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.7269. Min Act: -0.0000

Data Index: 774422 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 4.1874. Min Range: -4.1874

Max Act: 3.1068. Min Act: -0.0000

Data Index: 157556 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.8016. Min Act: -0.0000

Data Index: 96111 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.9116. Min Act: -0.0000

Data Index: 1137035 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.7425. Min Act: -0.0000

Data Index: 215035 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.4105. Min Act: -0.0000

Data Index: 483953 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 4.1874. Min Range: -4.1874

Max Act: 3.1204. Min Act: -0.0000

Data Index: 143439 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.8218. Min Act: -0.0000

Data Index: 97488 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.5107. Min Act: -0.0000

Data Index: 300177 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.7829. Min Act: -0.0000

Data Index: 888775 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.7715. Min Act: -0.0000

Data Index: 1036187 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 4.1874. Min Range: -4.1874

Max Act: 2.7450. Min Act: -0.0000

Data Index: 323521 (C4 (Web Text))

Max Activating Token Index: 133