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

Dataset: The Pile

Neuron 2164 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1205808 (The Pile)

Max Activating Token Index: 740

Text #1

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4471. Min Act: -0.0000

Data Index: 790082 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1552544 (The Pile)

Max Activating Token Index: 954

Text #3

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4793. Min Act: -0.0000

Data Index: 702749 (The Pile)

Max Activating Token Index: 832

Text #4

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4334. Min Act: -0.0000

Data Index: 428298 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1358742 (The Pile)

Max Activating Token Index: 214

Text #6

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1842555 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1739110 (The Pile)

Max Activating Token Index: 930

Text #8

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3755. Min Act: -0.0000

Data Index: 522026 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1669287 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3570. Min Act: 0.0001

Data Index: 1510204 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3575. Min Act: 0.0000

Data Index: 1903726 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3381. Min Act: 0.0000

Data Index: 552590 (The Pile)

Max Activating Token Index: 749

Text #13

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1207690 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3387. Min Act: 0.0000

Data Index: 359478 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1001770 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3226. Min Act: -0.0000

Data Index: 539296 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3329. Min Act: 0.0000

Data Index: 1594828 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3242. Min Act: 0.0000

Data Index: 593184 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3439. Min Act: -0.0000

Data Index: 979562 (The Pile)

Max Activating Token Index: 551