Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2220 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0003

Data Index: 163195 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0440. Min Act: -0.0003

Data Index: 503027 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0429. Min Act: -0.0003

Data Index: 364807 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0424. Min Act: -0.0003

Data Index: 893572 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0426. Min Act: -0.0003

Data Index: 1172970 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1298172 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0362. Min Act: -0.0003

Data Index: 156635 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0394. Min Act: -0.0003

Data Index: 185702 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0401. Min Act: -0.0003

Data Index: 676418 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0391. Min Act: -0.0003

Data Index: 35832 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0380. Min Act: -0.0003

Data Index: 141751 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1194324 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0386. Min Act: -0.0003

Data Index: 941044 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0392. Min Act: -0.0003

Data Index: 577974 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1180023 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0364. Min Act: -0.0003

Data Index: 14758 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1579887 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0381. Min Act: -0.0003

Data Index: 777908 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0365. Min Act: -0.0003

Data Index: 236473 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0364. Min Act: -0.0003

Data Index: 39245 (C4 (Web Text))

Max Activating Token Index: 51