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

Dataset: The Pile

Neuron 1017 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: 0.2316. Min Range: -0.2316

Max Act: 0.2316. Min Act: -0.0000

Data Index: 459270 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1489. Min Act: -0.0000

Data Index: 596469 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1383911 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1518038 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1331527 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1129. Min Act: -0.0000

Data Index: 254377 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1178. Min Act: -0.0000

Data Index: 589353 (The Pile)

Max Activating Token Index: 570

Text #7

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1082. Min Act: -0.0000

Data Index: 600455 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1037. Min Act: -0.0000

Data Index: 123048 (The Pile)

Max Activating Token Index: 805

Text #9

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1059. Min Act: -0.0000

Data Index: 205370 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.0907. Min Act: -0.0000

Data Index: 699647 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.0940. Min Act: -0.0000

Data Index: 905903 (The Pile)

Max Activating Token Index: 340

Text #12

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1008. Min Act: -0.0000

Data Index: 363468 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1644375 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.1000. Min Act: -0.0000

Data Index: 974776 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.0943. Min Act: -0.0000

Data Index: 106199 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1171400 (The Pile)

Max Activating Token Index: 333

Text #17

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1468235 (The Pile)

Max Activating Token Index: 54

Text #18

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.0978. Min Act: -0.0000

Data Index: 405649 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.2316. Min Range: -0.2316

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1579978 (The Pile)

Max Activating Token Index: 147