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

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

Neuron 1275 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2306. Min Act: -0.0000

Data Index: 679521 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.2123. Min Act: -0.0000

Data Index: 552402 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1670. Min Act: -0.0000

Data Index: 990673 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1835. Min Act: -0.0000

Data Index: 102433 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1436. Min Act: -0.0000

Data Index: 52701 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1521. Min Act: -0.0000

Data Index: 582268 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1502. Min Act: -0.0000

Data Index: 569179 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1565. Min Act: -0.0000

Data Index: 693907 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1498. Min Act: -0.0000

Data Index: 839420 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1420. Min Act: -0.0000

Data Index: 155693 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1550. Min Act: -0.0000

Data Index: 198634 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1110774 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1351. Min Act: -0.0000

Data Index: 493778 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1401. Min Act: -0.0000

Data Index: 2550 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1385739 (Python Code)

Max Activating Token Index: 117

Text #15

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1220285 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1561900 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1191. Min Act: -0.0000

Data Index: 491986 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1122. Min Act: -0.0000

Data Index: 775894 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.2306. Min Range: -0.2306

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1093226 (C4 (Web Text))

Max Activating Token Index: 123