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

Dataset: The Pile

Neuron 4092 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.3516. Min Act: -0.0000

Data Index: 1162969 (The Pile)

Max Activating Token Index: 185

Text #1

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.4414. Min Act: 0.0000

Data Index: 1783942 (The Pile)

Max Activating Token Index: 598

Text #2

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.6177. Min Act: -0.0000

Data Index: 866905 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.1796. Min Act: -0.0000

Data Index: 340852 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.7355. Min Act: -0.0000

Data Index: 1851185 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 3.6177. Min Range: -3.6177

Max Act: 3.1761. Min Act: -0.0000

Data Index: 635201 (The Pile)

Max Activating Token Index: 487

Text #6

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.9423. Min Act: -0.0000

Data Index: 1536418 (The Pile)

Max Activating Token Index: 929

Text #7

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.5677. Min Act: -0.0000

Data Index: 66068 (The Pile)

Max Activating Token Index: 877

Text #8

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.8266. Min Act: -0.0000

Data Index: 1686945 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.6916. Min Act: -0.0000

Data Index: 914432 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.6968. Min Act: -0.0000

Data Index: 268326 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.8148. Min Act: -0.0000

Data Index: 378049 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.6065. Min Act: -0.0000

Data Index: 1122375 (The Pile)

Max Activating Token Index: 514

Text #13

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.7195. Min Act: -0.0000

Data Index: 868420 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.5195. Min Act: -0.0000

Data Index: 179114 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.3766. Min Act: -0.0000

Data Index: 80436 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.4692. Min Act: -0.0000

Data Index: 1680712 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.4661. Min Act: -0.0000

Data Index: 633178 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.5769. Min Act: -0.0000

Data Index: 848315 (The Pile)

Max Activating Token Index: 900

Text #19

Max Range: 3.6177. Min Range: -3.6177

Max Act: 2.1823. Min Act: 0.0000

Data Index: 714665 (The Pile)

Max Activating Token Index: 824