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

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

Neuron 4788 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3885. Min Act: -0.0000

Data Index: 161164 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3681. Min Act: -0.0000

Data Index: 787556 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3523. Min Act: -0.0000

Data Index: 80260 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3486. Min Act: -0.0000

Data Index: 239583 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3470. Min Act: -0.0000

Data Index: 671920 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1100080 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1106643 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1273431 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1159907 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3048. Min Act: -0.0000

Data Index: 515286 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3153. Min Act: -0.0000

Data Index: 207867 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1221204 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3171. Min Act: -0.0000

Data Index: 368587 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1110965 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3369. Min Act: -0.0000

Data Index: 399508 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3193. Min Act: -0.0000

Data Index: 834657 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2796. Min Act: -0.0000

Data Index: 353724 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3321. Min Act: -0.0000

Data Index: 222282 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1327240 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3330. Min Act: -0.0000

Data Index: 891488 (C4 (Web Text))

Max Activating Token Index: 769