Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2367 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8441. Min Range: -2.8441

Max Act: 2.6877. Min Act: -0.0000

Data Index: 1072438 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 2.8441. Min Range: -2.8441

Max Act: 2.8441. Min Act: -0.0000

Data Index: 1196498 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 2.8441. Min Range: -2.8441

Max Act: 2.6998. Min Act: -0.0000

Data Index: 1363216 (Python Code)

Max Activating Token Index: 897

Text #3

Max Range: 2.8441. Min Range: -2.8441

Max Act: 2.3339. Min Act: -0.0000

Data Index: 686199 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 2.8441. Min Range: -2.8441

Max Act: 2.2444. Min Act: -0.0000

Data Index: 1620057 (Python Code)

Max Activating Token Index: 538

Text #5

Max Range: 2.8441. Min Range: -2.8441

Max Act: 2.1322. Min Act: -0.0000

Data Index: 44596 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 2.8441. Min Range: -2.8441

Max Act: 2.2312. Min Act: -0.0000

Data Index: 1445116 (Python Code)

Max Activating Token Index: 48

Text #7

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.9849. Min Act: -0.0000

Data Index: 1630022 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 2.8441. Min Range: -2.8441

Max Act: 2.0490. Min Act: -0.0000

Data Index: 1013328 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 2.8441. Min Range: -2.8441

Max Act: 2.0376. Min Act: -0.0000

Data Index: 1303359 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.9299. Min Act: -0.0000

Data Index: 1598972 (Python Code)

Max Activating Token Index: 470

Text #11

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.9265. Min Act: -0.0000

Data Index: 137145 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.9944. Min Act: -0.0000

Data Index: 1192543 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.8584. Min Act: -0.0000

Data Index: 1577039 (Python Code)

Max Activating Token Index: 883

Text #14

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.7505. Min Act: -0.0000

Data Index: 316663 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.8601. Min Act: -0.0000

Data Index: 680853 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.6535. Min Act: -0.0000

Data Index: 660244 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.6884. Min Act: -0.0000

Data Index: 126001 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.7513. Min Act: -0.0000

Data Index: 597587 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 2.8441. Min Range: -2.8441

Max Act: 1.8416. Min Act: -0.0000

Data Index: 597756 (C4 (Web Text))

Max Activating Token Index: 949