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

Dataset: The Pile

Neuron 134 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6339. Min Act: -0.0000

Data Index: 348201 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1508243 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6495. Min Act: 0.0000

Data Index: 1505185 (The Pile)

Max Activating Token Index: 691

Text #3

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5905. Min Act: -0.0000

Data Index: 450732 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6110. Min Act: -0.0000

Data Index: 624937 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1556680 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6164. Min Act: -0.0000

Data Index: 593342 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6038. Min Act: 0.0000

Data Index: 28281 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1173050 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1124518 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1652165 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1645020 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1070305 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1813101 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5405. Min Act: -0.0000

Data Index: 624825 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1125086 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1940770 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5005. Min Act: 0.0000

Data Index: 1660129 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.4826. Min Act: 0.0000

Data Index: 1212194 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1688938 (The Pile)

Max Activating Token Index: 132