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

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

Neuron 6092 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1183051 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1859. Min Act: -0.0001

Data Index: 1186182 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1011076 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1483. Min Act: -0.0000

Data Index: 674549 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1383. Min Act: -0.0001

Data Index: 212224 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1398. Min Act: -0.0001

Data Index: 91350 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1336. Min Act: -0.0001

Data Index: 458857 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1476. Min Act: -0.0000

Data Index: 45650 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1087400 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1648921 (Python Code)

Max Activating Token Index: 413

Text #10

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1554. Min Act: -0.0000

Data Index: 533291 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1246. Min Act: -0.0000

Data Index: 257892 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1130. Min Act: -0.0000

Data Index: 16341 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1200. Min Act: -0.0000

Data Index: 766273 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1553916 (Python Code)

Max Activating Token Index: 808

Text #15

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1327317 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.0941. Min Act: -0.0000

Data Index: 566624 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1173. Min Act: -0.0001

Data Index: 781518 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1216. Min Act: -0.0000

Data Index: 562191 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1496985 (Python Code)

Max Activating Token Index: 498