Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1159 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1520408 (Python Code)

Max Activating Token Index: 317

Text #1

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1377041 (Python Code)

Max Activating Token Index: 326

Text #2

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1587977 (Python Code)

Max Activating Token Index: 163

Text #3

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1613303 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1466592 (Python Code)

Max Activating Token Index: 719

Text #5

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1477203 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1504260 (Python Code)

Max Activating Token Index: 798

Text #7

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1639183 (Python Code)

Max Activating Token Index: 596

Text #8

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1479890 (Python Code)

Max Activating Token Index: 660

Text #9

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1276. Min Act: -0.0001

Data Index: 295359 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1228842 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1496245 (Python Code)

Max Activating Token Index: 300

Text #12

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1502538 (Python Code)

Max Activating Token Index: 215

Text #13

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1383662 (Python Code)

Max Activating Token Index: 591

Text #14

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1178684 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1628426 (Python Code)

Max Activating Token Index: 261

Text #16

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1362003 (Python Code)

Max Activating Token Index: 785

Text #17

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1505517 (Python Code)

Max Activating Token Index: 718

Text #18

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1219. Min Act: -0.0001

Data Index: 318091 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1394094 (Python Code)

Max Activating Token Index: 296