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

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

Neuron 3002 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.4203. Min Act: -0.0001

Data Index: 61943 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3126. Min Act: -0.0001

Data Index: 429091 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3562. Min Act: -0.0001

Data Index: 1071850 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3275. Min Act: -0.0001

Data Index: 346130 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3582. Min Act: -0.0001

Data Index: 213848 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3170. Min Act: -0.0001

Data Index: 1465891 (Python Code)

Max Activating Token Index: 156

Text #6

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3164. Min Act: -0.0001

Data Index: 1121458 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3175. Min Act: -0.0001

Data Index: 394255 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3149. Min Act: -0.0001

Data Index: 107656 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3352. Min Act: -0.0001

Data Index: 1254416 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3241. Min Act: -0.0001

Data Index: 1143551 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3186. Min Act: -0.0001

Data Index: 765894 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.2962. Min Act: -0.0001

Data Index: 652903 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3127. Min Act: -0.0001

Data Index: 789310 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3006. Min Act: -0.0001

Data Index: 1182828 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3222. Min Act: -0.0001

Data Index: 1149511 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3124. Min Act: -0.0001

Data Index: 113456 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.2978. Min Act: -0.0001

Data Index: 123147 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3091. Min Act: -0.0001

Data Index: 299988 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.2979. Min Act: -0.0001

Data Index: 1456652 (Python Code)

Max Activating Token Index: 937