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

Dataset: The Pile

Neuron 1040 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: 0.2151. Min Range: -0.2151

Max Act: 0.2151. Min Act: -0.0000

Data Index: 923821 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1733. Min Act: -0.0000

Data Index: 474145 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1707. Min Act: -0.0000

Data Index: 302666 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1478. Min Act: -0.0000

Data Index: 884528 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1416. Min Act: -0.0000

Data Index: 377368 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1453. Min Act: -0.0000

Data Index: 428977 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1267048 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1019591 (The Pile)

Max Activating Token Index: 819

Text #8

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1208284 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1389. Min Act: -0.0000

Data Index: 860279 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1291. Min Act: -0.0000

Data Index: 833627 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1187. Min Act: -0.0000

Data Index: 499786 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1544733 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1209. Min Act: -0.0000

Data Index: 508255 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1642858 (The Pile)

Max Activating Token Index: 590

Text #15

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1863669 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1419505 (The Pile)

Max Activating Token Index: 726

Text #17

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1156. Min Act: -0.0000

Data Index: 684659 (The Pile)

Max Activating Token Index: 854

Text #18

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1104. Min Act: -0.0000

Data Index: 126348 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1344557 (The Pile)

Max Activating Token Index: 455