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

Dataset: The Pile

Neuron 2728 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1571209 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5327. Min Act: -0.0000

Data Index: 849634 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1819650 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5102. Min Act: -0.0000

Data Index: 733055 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1375854 (The Pile)

Max Activating Token Index: 269

Text #5

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1403574 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1486821 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1422405 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4351. Min Act: -0.0000

Data Index: 659290 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1586358 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.3932. Min Act: -0.0000

Data Index: 633561 (The Pile)

Max Activating Token Index: 2

Text #11

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.3932. Min Act: -0.0000

Data Index: 360267 (The Pile)

Max Activating Token Index: 2

Text #12

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.3614. Min Act: -0.0000

Data Index: 334495 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.3995. Min Act: -0.0000

Data Index: 502020 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1522539 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4206. Min Act: -0.0000

Data Index: 91858 (The Pile)

Max Activating Token Index: 198

Text #16

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.3630. Min Act: -0.0000

Data Index: 850002 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.4027. Min Act: -0.0000

Data Index: 15954 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.3418. Min Act: -0.0000

Data Index: 948877 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.6521. Min Range: -0.6521

Max Act: 0.3577. Min Act: -0.0000

Data Index: 389751 (The Pile)

Max Activating Token Index: 802