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

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

Neuron 3801 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1344031 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1228479 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1905. Min Act: -0.0000

Data Index: 93730 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.2195. Min Act: -0.0000

Data Index: 838165 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1011887 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1782. Min Act: -0.0000

Data Index: 536443 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1691. Min Act: -0.0000

Data Index: 328334 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1547. Min Act: -0.0000

Data Index: 105640 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1477. Min Act: -0.0000

Data Index: 210878 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1416. Min Act: -0.0000

Data Index: 611418 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1424. Min Act: -0.0000

Data Index: 76895 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1424257 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1060937 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1597963 (Python Code)

Max Activating Token Index: 335

Text #14

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1418. Min Act: -0.0000

Data Index: 254451 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1226. Min Act: -0.0000

Data Index: 751549 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1279. Min Act: -0.0000

Data Index: 79643 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1254. Min Act: -0.0000

Data Index: 993552 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1490087 (Python Code)

Max Activating Token Index: 335

Text #19

Max Range: 0.2542. Min Range: -0.2542

Max Act: 0.1210. Min Act: -0.0000

Data Index: 221331 (C4 (Web Text))

Max Activating Token Index: 24