Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1982 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.9106. Min Act: -0.0001

Data Index: 893419 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8968. Min Act: -0.0001

Data Index: 773176 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.9252. Min Act: -0.0001

Data Index: 729327 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8553. Min Act: -0.0001

Data Index: 1216660 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8446. Min Act: -0.0001

Data Index: 1192636 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8194. Min Act: -0.0001

Data Index: 236081 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8210. Min Act: -0.0001

Data Index: 692474 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8131. Min Act: -0.0001

Data Index: 610813 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8164. Min Act: -0.0001

Data Index: 278146 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8144. Min Act: -0.0001

Data Index: 1191495 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8112. Min Act: -0.0001

Data Index: 681578 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7984. Min Act: -0.0001

Data Index: 1121420 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7914. Min Act: -0.0001

Data Index: 35714 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8113. Min Act: -0.0001

Data Index: 534475 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7376. Min Act: -0.0001

Data Index: 164550 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7752. Min Act: -0.0001

Data Index: 1115508 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7924. Min Act: -0.0001

Data Index: 574273 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7366. Min Act: -0.0001

Data Index: 1327315 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7601. Min Act: -0.0001

Data Index: 482114 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8015. Min Act: -0.0001

Data Index: 1172187 (C4 (Web Text))

Max Activating Token Index: 71