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

Dataset: The Pile

Neuron 123 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: 1.7603. Min Range: -1.7603

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1851877 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.7161. Min Act: -0.0000

Data Index: 276598 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.6069. Min Act: -0.0000

Data Index: 90211 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.4179. Min Act: -0.0000

Data Index: 47638 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.4252. Min Act: -0.0000

Data Index: 641301 (The Pile)

Max Activating Token Index: 394

Text #5

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5168. Min Act: -0.0000

Data Index: 1052831 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.7603. Min Act: -0.0000

Data Index: 218803 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.3571. Min Act: -0.0000

Data Index: 1183537 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.6446. Min Act: -0.0000

Data Index: 270260 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5567. Min Act: -0.0000

Data Index: 1346841 (The Pile)

Max Activating Token Index: 634

Text #10

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.3526. Min Act: -0.0000

Data Index: 24382 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5135. Min Act: -0.0000

Data Index: 340204 (The Pile)

Max Activating Token Index: 359

Text #12

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.4202. Min Act: -0.0000

Data Index: 230953 (The Pile)

Max Activating Token Index: 358

Text #13

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1838095 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.4870. Min Act: -0.0000

Data Index: 1080120 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.4021. Min Act: -0.0000

Data Index: 415054 (The Pile)

Max Activating Token Index: 347

Text #16

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.2995. Min Act: -0.0000

Data Index: 1177554 (The Pile)

Max Activating Token Index: 552

Text #17

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.3495. Min Act: -0.0000

Data Index: 450849 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1548402 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.3372. Min Act: -0.0000

Data Index: 792471 (The Pile)

Max Activating Token Index: 532