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

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

Neuron 3756 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3335. Min Act: -0.0001

Data Index: 977121 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3415. Min Act: -0.0001

Data Index: 126153 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3295. Min Act: -0.0001

Data Index: 974709 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3162. Min Act: -0.0001

Data Index: 476066 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3212. Min Act: -0.0001

Data Index: 934791 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2985. Min Act: -0.0001

Data Index: 1273027 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1148319 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2967. Min Act: -0.0001

Data Index: 125757 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3083. Min Act: -0.0001

Data Index: 241777 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3167. Min Act: -0.0001

Data Index: 1063738 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3172. Min Act: -0.0001

Data Index: 168853 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3109. Min Act: -0.0001

Data Index: 919234 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3021. Min Act: -0.0001

Data Index: 172467 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2805. Min Act: -0.0001

Data Index: 1078041 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2883. Min Act: -0.0001

Data Index: 684939 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2872. Min Act: -0.0001

Data Index: 1111490 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2824. Min Act: -0.0001

Data Index: 23 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2882. Min Act: -0.0001

Data Index: 42913 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2758. Min Act: -0.0001

Data Index: 418963 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2860. Min Act: -0.0001

Data Index: 876034 (C4 (Web Text))

Max Activating Token Index: 645