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

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

Neuron 4777 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: 0.2160. Min Range: -0.2160

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1099216 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1817. Min Act: -0.0001

Data Index: 1575020 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1682. Min Act: -0.0000

Data Index: 1247248 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1727. Min Act: -0.0001

Data Index: 1520884 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1553915 (Python Code)

Max Activating Token Index: 535

Text #5

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1484264 (Python Code)

Max Activating Token Index: 139

Text #6

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1606. Min Act: -0.0001

Data Index: 1505995 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1483145 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1548. Min Act: -0.0001

Data Index: 1368014 (Python Code)

Max Activating Token Index: 319

Text #9

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1612342 (Python Code)

Max Activating Token Index: 257

Text #10

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1554455 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1545448 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1542601 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1406935 (Python Code)

Max Activating Token Index: 798

Text #14

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1381902 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1619619 (Python Code)

Max Activating Token Index: 215

Text #16

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1489902 (Python Code)

Max Activating Token Index: 385

Text #17

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1224213 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1364. Min Act: -0.0000

Data Index: 991592 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1446808 (Python Code)

Max Activating Token Index: 384