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

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

Neuron 3006 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.2317. Min Act: -0.0000

Data Index: 229510 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.3428. Min Act: -0.0000

Data Index: 289580 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.3184. Min Act: -0.0000

Data Index: 647945 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.2108. Min Act: -0.0000

Data Index: 610867 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.1827. Min Act: -0.0000

Data Index: 636808 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.4167. Min Act: -0.0000

Data Index: 851515 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.1590. Min Act: -0.0000

Data Index: 359513 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.3562. Min Act: -0.0000

Data Index: 273065 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.2585. Min Act: -0.0000

Data Index: 808819 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.2578. Min Act: -0.0000

Data Index: 925522 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.4557. Min Act: -0.0000

Data Index: 288061 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.1733. Min Act: -0.0000

Data Index: 1262791 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.0931. Min Act: -0.0000

Data Index: 728195 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.0442. Min Act: -0.0000

Data Index: 851724 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.1427. Min Act: -0.0000

Data Index: 385608 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.1178. Min Act: -0.0000

Data Index: 677983 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.2337. Min Act: -0.0000

Data Index: 718421 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.1063. Min Act: -0.0000

Data Index: 503190 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.3091. Min Act: -0.0000

Data Index: 714367 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 2.4557. Min Range: -2.4557

Max Act: 2.2361. Min Act: -0.0000

Data Index: 16132 (C4 (Web Text))

Max Activating Token Index: 541