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

Dataset: The Pile

Neuron 3099 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: 0.7094. Min Range: -0.7094

Max Act: 0.6449. Min Act: -0.0000

Data Index: 776356 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1199836 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6541. Min Act: -0.0000

Data Index: 876824 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1834585 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.7094. Min Act: -0.0000

Data Index: 52766 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1602863 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1441694 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5651. Min Act: -0.0000

Data Index: 551994 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6505. Min Act: -0.0000

Data Index: 394955 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6283. Min Act: -0.0000

Data Index: 76811 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1587970 (The Pile)

Max Activating Token Index: 455

Text #11

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6151. Min Act: -0.0000

Data Index: 506463 (The Pile)

Max Activating Token Index: 132

Text #12

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1779449 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5933. Min Act: -0.0000

Data Index: 83383 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5833. Min Act: -0.0000

Data Index: 291871 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6263. Min Act: -0.0000

Data Index: 789190 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5354. Min Act: -0.0000

Data Index: 126206 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5712. Min Act: -0.0000

Data Index: 558856 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6110. Min Act: -0.0000

Data Index: 534468 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1054290 (The Pile)

Max Activating Token Index: 421