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

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

Neuron 2715 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.8036. Min Act: -0.0000

Data Index: 1572788 (Python Code)

Max Activating Token Index: 834

Text #1

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.7608. Min Act: -0.0000

Data Index: 1490311 (Python Code)

Max Activating Token Index: 197

Text #2

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.5683. Min Act: -0.0000

Data Index: 1533552 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.3529. Min Act: -0.0000

Data Index: 1647684 (Python Code)

Max Activating Token Index: 94

Text #4

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.3874. Min Act: -0.0000

Data Index: 456883 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.3411. Min Act: -0.0000

Data Index: 1429742 (Python Code)

Max Activating Token Index: 596

Text #6

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.3117. Min Act: -0.0000

Data Index: 557814 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1458204 (Python Code)

Max Activating Token Index: 947

Text #8

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.2177. Min Act: -0.0000

Data Index: 176198 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.2576. Min Act: -0.0000

Data Index: 489682 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.3302. Min Act: -0.0000

Data Index: 903979 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1620003 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.1182. Min Act: -0.0000

Data Index: 1487640 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.2396. Min Act: -0.0000

Data Index: 1159083 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.1421. Min Act: -0.0000

Data Index: 976139 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1413969 (Python Code)

Max Activating Token Index: 348

Text #16

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.2467. Min Act: -0.0000

Data Index: 645725 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1166868 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.0106. Min Act: -0.0000

Data Index: 913372 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 1.8036. Min Range: -1.8036

Max Act: 0.9829. Min Act: -0.0000

Data Index: 180210 (C4 (Web Text))

Max Activating Token Index: 344