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

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

Neuron 1253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.3152. Min Act: -0.0000

Data Index: 224170 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.3265. Min Act: -0.0000

Data Index: 871528 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2979. Min Act: -0.0000

Data Index: 683069 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1200204 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2701. Min Act: -0.0000

Data Index: 664354 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2726. Min Act: -0.0000

Data Index: 999779 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2616. Min Act: -0.0000

Data Index: 987657 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2774. Min Act: -0.0000

Data Index: 489387 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2683. Min Act: -0.0000

Data Index: 935137 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2680. Min Act: -0.0000

Data Index: 634590 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2743. Min Act: -0.0000

Data Index: 58239 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2700. Min Act: -0.0000

Data Index: 708028 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2689. Min Act: -0.0000

Data Index: 363893 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2595. Min Act: -0.0000

Data Index: 59382 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2512. Min Act: -0.0000

Data Index: 228053 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1258504 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2509. Min Act: -0.0000

Data Index: 660020 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2529. Min Act: -0.0000

Data Index: 560187 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2519. Min Act: -0.0000

Data Index: 305017 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2568. Min Act: -0.0000

Data Index: 342469 (C4 (Web Text))

Max Activating Token Index: 502