Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1959 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3587. Min Act: -0.0002

Data Index: 1103065 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3506. Min Act: -0.0002

Data Index: 150112 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3398. Min Act: -0.0002

Data Index: 371984 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3325. Min Act: -0.0002

Data Index: 1185999 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3218. Min Act: -0.0002

Data Index: 1242391 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3171. Min Act: -0.0003

Data Index: 862989 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3152. Min Act: -0.0003

Data Index: 136414 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3127. Min Act: -0.0002

Data Index: 428069 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3067. Min Act: -0.0002

Data Index: 830608 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3049. Min Act: -0.0002

Data Index: 928471 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2848. Min Act: -0.0002

Data Index: 940076 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3061. Min Act: -0.0002

Data Index: 1020676 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.3049. Min Act: -0.0002

Data Index: 605970 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2998. Min Act: -0.0002

Data Index: 917978 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2962. Min Act: -0.0002

Data Index: 543203 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2993. Min Act: -0.0002

Data Index: 629274 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2989. Min Act: -0.0002

Data Index: 326046 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2947. Min Act: -0.0003

Data Index: 55474 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2933. Min Act: -0.0002

Data Index: 5903 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.3587. Min Range: -0.3587

Max Act: 0.2912. Min Act: -0.0002

Data Index: 486591 (C4 (Web Text))

Max Activating Token Index: 806