Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2534 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2150. Min Range: -1.2150

Max Act: 1.2150. Min Act: -0.0000

Data Index: 433097 (The Pile)

Max Activating Token Index: 265

Text #1

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1183581 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1195689 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7426. Min Act: -0.0000

Data Index: 329441 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1782303 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1577733 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1790466 (The Pile)

Max Activating Token Index: 230

Text #7

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1221567 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7747. Min Act: -0.0000

Data Index: 769206 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1851357 (The Pile)

Max Activating Token Index: 164

Text #10

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.6628. Min Act: -0.0000

Data Index: 636107 (The Pile)

Max Activating Token Index: 722

Text #11

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7292. Min Act: -0.0000

Data Index: 712162 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.6940. Min Act: -0.0000

Data Index: 914338 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1264510 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7293. Min Act: -0.0000

Data Index: 938624 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1595082 (The Pile)

Max Activating Token Index: 104

Text #16

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7185. Min Act: -0.0000

Data Index: 264407 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1217745 (The Pile)

Max Activating Token Index: 817

Text #18

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1729070 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 1.2150. Min Range: -1.2150

Max Act: 0.6419. Min Act: -0.0000

Data Index: 829538 (The Pile)

Max Activating Token Index: 360