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

Dataset: The Pile

Neuron 2924 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.6297. Min Act: -0.0000

Data Index: 368730 (The Pile)

Max Activating Token Index: 186

Text #1

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.3345. Min Act: -0.0000

Data Index: 1758632 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1966433 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.9153. Min Act: -0.0000

Data Index: 720627 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.0319. Min Act: -0.0000

Data Index: 396252 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.9764. Min Act: 0.0000

Data Index: 580529 (The Pile)

Max Activating Token Index: 924

Text #6

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.0084. Min Act: -0.0000

Data Index: 633741 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.8849. Min Act: -0.0000

Data Index: 883870 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.8414. Min Act: -0.0000

Data Index: 985893 (The Pile)

Max Activating Token Index: 186

Text #9

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.9342. Min Act: 0.0000

Data Index: 1205491 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1451322 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.7451. Min Act: -0.0000

Data Index: 681826 (The Pile)

Max Activating Token Index: 787

Text #12

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1460224 (The Pile)

Max Activating Token Index: 294

Text #13

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1232405 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.6942. Min Act: -0.0000

Data Index: 76928 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1322428 (The Pile)

Max Activating Token Index: 284

Text #16

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1105802 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.7201. Min Act: 0.0000

Data Index: 673160 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.7123. Min Act: -0.0000

Data Index: 447364 (The Pile)

Max Activating Token Index: 215

Text #19

Max Range: 1.6297. Min Range: -1.6297

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1735735 (The Pile)

Max Activating Token Index: 649