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

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

Neuron 2839 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.6253. Min Act: -0.0000

Data Index: 612290 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.6023. Min Act: -0.0000

Data Index: 56283 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5585. Min Act: -0.0000

Data Index: 392234 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5389. Min Act: -0.0000

Data Index: 648907 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5066. Min Act: -0.0000

Data Index: 224543 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1180528 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5094. Min Act: -0.0000

Data Index: 162837 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1313716 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4891. Min Act: -0.0000

Data Index: 701228 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1032141 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4529. Min Act: -0.0000

Data Index: 163161 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1074357 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1239380 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1102666 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1173685 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1213981 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4125. Min Act: -0.0000

Data Index: 107940 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1199156 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4256. Min Act: -0.0000

Data Index: 216573 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4230. Min Act: -0.0000

Data Index: 85663 (C4 (Web Text))

Max Activating Token Index: 370