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

Dataset: The Pile

Neuron 149 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: 0.4521. Min Range: -0.4521

Max Act: 0.4335. Min Act: -0.0000

Data Index: 925310 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1468396 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4273. Min Act: -0.0000

Data Index: 41047 (The Pile)

Max Activating Token Index: 792

Text #3

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4152. Min Act: 0.0000

Data Index: 1965105 (The Pile)

Max Activating Token Index: 371

Text #4

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1135915 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1355114 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1913378 (The Pile)

Max Activating Token Index: 521

Text #7

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1890354 (The Pile)

Max Activating Token Index: 388

Text #8

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1992017 (The Pile)

Max Activating Token Index: 133

Text #9

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1762168 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1666383 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1034059 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4261. Min Act: 0.0000

Data Index: 1954304 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1404524 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4152. Min Act: -0.0000

Data Index: 477589 (The Pile)

Max Activating Token Index: 237

Text #15

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3910. Min Act: -0.0000

Data Index: 541101 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4521. Min Act: -0.0000

Data Index: 726288 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1354834 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1912715 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1300021 (The Pile)

Max Activating Token Index: 788