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

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

Neuron 233 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1122532 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.3205. Min Act: -0.0000

Data Index: 32753 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.3136. Min Act: -0.0000

Data Index: 668783 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.3039. Min Act: -0.0000

Data Index: 463542 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.3153. Min Act: -0.0000

Data Index: 649159 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.3091. Min Act: -0.0000

Data Index: 989032 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2522. Min Act: -0.0001

Data Index: 1588112 (Python Code)

Max Activating Token Index: 735

Text #7

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1383605 (Python Code)

Max Activating Token Index: 113

Text #8

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2744. Min Act: -0.0001

Data Index: 901575 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2825. Min Act: -0.0001

Data Index: 1146904 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2563. Min Act: -0.0000

Data Index: 926897 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2630. Min Act: -0.0001

Data Index: 1432903 (Python Code)

Max Activating Token Index: 395

Text #12

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1134841 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2635. Min Act: -0.0001

Data Index: 1538744 (Python Code)

Max Activating Token Index: 75

Text #14

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2557. Min Act: -0.0000

Data Index: 591951 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2437. Min Act: -0.0000

Data Index: 266505 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2689. Min Act: -0.0000

Data Index: 166547 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2652. Min Act: -0.0000

Data Index: 530895 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2635. Min Act: -0.0001

Data Index: 1448565 (Python Code)

Max Activating Token Index: 542

Text #19

Max Range: 0.3205. Min Range: -0.3205

Max Act: 0.2463. Min Act: -0.0001

Data Index: 204027 (C4 (Web Text))

Max Activating Token Index: 281