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

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

Neuron 3587 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1141614 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.5082. Min Act: -0.0000

Data Index: 542811 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4168. Min Act: -0.0000

Data Index: 329415 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3981. Min Act: -0.0000

Data Index: 714413 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3843. Min Act: -0.0000

Data Index: 302933 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3882. Min Act: 0.0000

Data Index: 799546 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3884. Min Act: -0.0000

Data Index: 835822 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3638. Min Act: -0.0000

Data Index: 858333 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3666. Min Act: -0.0000

Data Index: 260811 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3560. Min Act: -0.0000

Data Index: 718812 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1256588 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3487. Min Act: -0.0000

Data Index: 232027 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3432. Min Act: 0.0000

Data Index: 1115787 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3605. Min Act: -0.0000

Data Index: 200262 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3459. Min Act: -0.0000

Data Index: 691091 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1162224 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3255. Min Act: -0.0000

Data Index: 650545 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3269. Min Act: -0.0000

Data Index: 457408 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3062. Min Act: -0.0000

Data Index: 725126 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1268574 (C4 (Web Text))

Max Activating Token Index: 956