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

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

Neuron 323 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.4465. Min Act: -0.0000

Data Index: 716999 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1466193 (Python Code)

Max Activating Token Index: 896

Text #2

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1485187 (Python Code)

Max Activating Token Index: 490

Text #3

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3862. Min Act: -0.0000

Data Index: 249116 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1545725 (Python Code)

Max Activating Token Index: 68

Text #5

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3577. Min Act: -0.0000

Data Index: 335805 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1622526 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3531. Min Act: -0.0000

Data Index: 631402 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3334. Min Act: -0.0000

Data Index: 215262 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3358. Min Act: -0.0000

Data Index: 762743 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1404936 (Python Code)

Max Activating Token Index: 380

Text #11

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1020131 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3150. Min Act: -0.0000

Data Index: 730510 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3234. Min Act: -0.0000

Data Index: 742160 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1215412 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1019623 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3032. Min Act: -0.0000

Data Index: 271464 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3056. Min Act: -0.0000

Data Index: 305364 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1016158 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.2876. Min Act: -0.0000

Data Index: 59682 (C4 (Web Text))

Max Activating Token Index: 661