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

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

Neuron 3124 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3505. Min Act: -0.0003

Data Index: 1161203 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3448. Min Act: -0.0003

Data Index: 541421 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2892. Min Act: -0.0003

Data Index: 457941 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2653. Min Act: -0.0003

Data Index: 1303039 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2838. Min Act: -0.0003

Data Index: 1168002 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2786. Min Act: -0.0003

Data Index: 925403 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2736. Min Act: -0.0003

Data Index: 1349364 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2523. Min Act: -0.0003

Data Index: 1205379 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2387. Min Act: -0.0003

Data Index: 946180 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2625. Min Act: -0.0003

Data Index: 143383 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2518. Min Act: -0.0003

Data Index: 306757 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2585. Min Act: -0.0003

Data Index: 547601 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2667. Min Act: -0.0003

Data Index: 500770 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2549. Min Act: -0.0003

Data Index: 411190 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2551. Min Act: -0.0003

Data Index: 653821 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2530. Min Act: -0.0003

Data Index: 882406 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2440. Min Act: -0.0003

Data Index: 472830 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2522. Min Act: -0.0003

Data Index: 1288597 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2504. Min Act: -0.0003

Data Index: 332914 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2444. Min Act: -0.0003

Data Index: 625733 (C4 (Web Text))

Max Activating Token Index: 332