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

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

Neuron 5427 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: 0.1545. Min Range: -0.1545

Max Act: 0.1545. Min Act: -0.0000

Data Index: 559043 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1318. Min Act: -0.0000

Data Index: 439023 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1281. Min Act: -0.0000

Data Index: 241601 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1378948 (Python Code)

Max Activating Token Index: 59

Text #4

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1316. Min Act: -0.0000

Data Index: 198691 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1269. Min Act: -0.0000

Data Index: 1079537 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1063734 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1279. Min Act: -0.0000

Data Index: 83023 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1306437 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1609802 (Python Code)

Max Activating Token Index: 309

Text #10

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1200. Min Act: -0.0000

Data Index: 343381 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1423529 (Python Code)

Max Activating Token Index: 130

Text #12

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1272. Min Act: -0.0000

Data Index: 517782 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1608341 (Python Code)

Max Activating Token Index: 283

Text #14

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1621986 (Python Code)

Max Activating Token Index: 168

Text #15

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1292. Min Act: -0.0000

Data Index: 717261 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1377618 (Python Code)

Max Activating Token Index: 880

Text #17

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1196. Min Act: -0.0000

Data Index: 787787 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1652229 (Python Code)

Max Activating Token Index: 874

Text #19

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1493894 (Python Code)

Max Activating Token Index: 829