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

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

Neuron 4493 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3326. Min Range: -4.3326

Max Act: 4.3326. Min Act: -0.0000

Data Index: 184552 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.8140. Min Act: -0.0000

Data Index: 912811 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.8211. Min Act: -0.0000

Data Index: 445469 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.6274. Min Act: -0.0000

Data Index: 643609 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.7918. Min Act: -0.0000

Data Index: 615872 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.9454. Min Act: -0.0000

Data Index: 913907 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.7275. Min Act: -0.0000

Data Index: 435126 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.7361. Min Act: -0.0000

Data Index: 990709 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.4083. Min Act: -0.0000

Data Index: 1257755 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.7204. Min Act: -0.0000

Data Index: 223821 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.3823. Min Act: -0.0000

Data Index: 813164 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.6907. Min Act: -0.0000

Data Index: 683315 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.5072. Min Act: -0.0000

Data Index: 701174 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.3535. Min Act: -0.0000

Data Index: 547327 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.3381. Min Act: -0.0000

Data Index: 993617 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.5668. Min Act: -0.0000

Data Index: 1072049 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.4059. Min Act: -0.0000

Data Index: 764547 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.2577. Min Act: -0.0000

Data Index: 30970 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.2423. Min Act: -0.0000

Data Index: 693113 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 4.3326. Min Range: -4.3326

Max Act: 3.4171. Min Act: -0.0000

Data Index: 617213 (C4 (Web Text))

Max Activating Token Index: 844