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

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

Neuron 4989 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: 0.1566. Min Range: -0.1566

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1599454 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1397. Min Act: -0.0000

Data Index: 160924 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1485128 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1613418 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1600244 (Python Code)

Max Activating Token Index: 131

Text #5

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1449658 (Python Code)

Max Activating Token Index: 974

Text #6

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1163728 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1587083 (Python Code)

Max Activating Token Index: 52

Text #8

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1276. Min Act: -0.0000

Data Index: 586657 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1230. Min Act: -0.0000

Data Index: 519744 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1231. Min Act: -0.0000

Data Index: 34182 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1261. Min Act: -0.0000

Data Index: 467554 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1403220 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1318. Min Act: -0.0000

Data Index: 235489 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1251. Min Act: -0.0000

Data Index: 639684 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1153435 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1080948 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1308. Min Act: -0.0000

Data Index: 349949 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1414673 (Python Code)

Max Activating Token Index: 812

Text #19

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1552335 (Python Code)

Max Activating Token Index: 24