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

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

Neuron 2762 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1448. Min Act: -0.0002

Data Index: 25096 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1134994 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0972. Min Act: -0.0002

Data Index: 149936 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1002. Min Act: -0.0002

Data Index: 76231 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0930. Min Act: -0.0002

Data Index: 575936 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0924. Min Act: -0.0002

Data Index: 322823 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0957. Min Act: -0.0002

Data Index: 762389 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1068232 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0916. Min Act: -0.0002

Data Index: 192547 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1305059 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0893. Min Act: -0.0002

Data Index: 564534 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1082441 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1104520 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1077503 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0913. Min Act: -0.0002

Data Index: 847390 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0855. Min Act: -0.0002

Data Index: 272489 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0968. Min Act: -0.0002

Data Index: 78877 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0862. Min Act: -0.0002

Data Index: 987276 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0905. Min Act: -0.0002

Data Index: 611596 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0819. Min Act: -0.0002

Data Index: 263394 (C4 (Web Text))

Max Activating Token Index: 225