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

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

Neuron 1104 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9760. Min Range: -2.9760

Max Act: 2.9760. Min Act: -0.0000

Data Index: 36448 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 2.9760. Min Range: -2.9760

Max Act: 2.4407. Min Act: -0.0000

Data Index: 96571 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 2.9760. Min Range: -2.9760

Max Act: 2.4092. Min Act: -0.0000

Data Index: 820047 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 2.9760. Min Range: -2.9760

Max Act: 2.3225. Min Act: -0.0000

Data Index: 107062 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 2.9760. Min Range: -2.9760

Max Act: 2.1374. Min Act: -0.0000

Data Index: 163190 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 2.9760. Min Range: -2.9760

Max Act: 2.1358. Min Act: -0.0000

Data Index: 22478 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 2.9760. Min Range: -2.9760

Max Act: 2.2196. Min Act: -0.0000

Data Index: 1182714 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 2.9760. Min Range: -2.9760

Max Act: 2.0007. Min Act: -0.0000

Data Index: 45388 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 2.9760. Min Range: -2.9760

Max Act: 1.9488. Min Act: -0.0000

Data Index: 488340 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 2.9760. Min Range: -2.9760

Max Act: 2.0347. Min Act: -0.0000

Data Index: 1034993 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 2.9760. Min Range: -2.9760

Max Act: 1.8097. Min Act: -0.0000

Data Index: 862361 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 2.9760. Min Range: -2.9760

Max Act: 2.0060. Min Act: -0.0000

Data Index: 281532 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 2.9760. Min Range: -2.9760

Max Act: 1.7280. Min Act: -0.0000

Data Index: 1001637 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 2.9760. Min Range: -2.9760

Max Act: 1.6179. Min Act: -0.0000

Data Index: 991825 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 2.9760. Min Range: -2.9760

Max Act: 1.7923. Min Act: -0.0000

Data Index: 123362 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 2.9760. Min Range: -2.9760

Max Act: 1.9034. Min Act: -0.0000

Data Index: 171389 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 2.9760. Min Range: -2.9760

Max Act: 1.7504. Min Act: -0.0000

Data Index: 998636 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 2.9760. Min Range: -2.9760

Max Act: 1.7445. Min Act: -0.0000

Data Index: 1226703 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 2.9760. Min Range: -2.9760

Max Act: 1.7195. Min Act: -0.0000

Data Index: 1061007 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 2.9760. Min Range: -2.9760

Max Act: 1.5409. Min Act: -0.0000

Data Index: 857862 (C4 (Web Text))

Max Activating Token Index: 837