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

Dataset: The Pile

Neuron 3211 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1415946 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1606. Min Act: -0.0000

Data Index: 214525 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1404. Min Act: -0.0000

Data Index: 934316 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1650671 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1477887 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1117045 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1877326 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1200061 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1219796 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1743137 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1239. Min Act: -0.0000

Data Index: 133968 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1450629 (The Pile)

Max Activating Token Index: 327

Text #12

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1177. Min Act: -0.0000

Data Index: 894283 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1285. Min Act: -0.0000

Data Index: 283265 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1294. Min Act: -0.0000

Data Index: 50617 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1204. Min Act: -0.0000

Data Index: 467309 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1330. Min Act: -0.0000

Data Index: 266620 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1274. Min Act: -0.0000

Data Index: 271759 (The Pile)

Max Activating Token Index: 534

Text #18

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1871145 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1218. Min Act: -0.0000

Data Index: 368108 (The Pile)

Max Activating Token Index: 518