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

Dataset: The Pile

Neuron 643 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1198. Min Range: -1.1198

Max Act: 1.0692. Min Act: -0.0000

Data Index: 476294 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 1.1198. Min Range: -1.1198

Max Act: 1.1198. Min Act: -0.0000

Data Index: 700593 (The Pile)

Max Activating Token Index: 366

Text #2

Max Range: 1.1198. Min Range: -1.1198

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1241924 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1716239 (The Pile)

Max Activating Token Index: 728

Text #4

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.6777. Min Act: -0.0000

Data Index: 301559 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.7281. Min Act: -0.0000

Data Index: 904078 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.7017. Min Act: -0.0000

Data Index: 625406 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.7442. Min Act: -0.0000

Data Index: 70384 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.7128. Min Act: -0.0000

Data Index: 651008 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.7415. Min Act: -0.0001

Data Index: 1290979 (The Pile)

Max Activating Token Index: 675

Text #10

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1526812 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.6640. Min Act: -0.0000

Data Index: 920017 (The Pile)

Max Activating Token Index: 400

Text #12

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1497837 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1243595 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1350042 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1672403 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.6390. Min Act: -0.0000

Data Index: 513469 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1532039 (The Pile)

Max Activating Token Index: 853

Text #18

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.5411. Min Act: -0.0000

Data Index: 602900 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 1.1198. Min Range: -1.1198

Max Act: 0.6160. Min Act: -0.0000

Data Index: 163423 (The Pile)

Max Activating Token Index: 271