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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2795 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0864. Min Act: -0.0000

Data Index: 522183 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1164177 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.7039. Min Act: -0.0000

Data Index: 1262899 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.4858. Min Act: -0.0001

Data Index: 968894 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.5677. Min Act: -0.0000

Data Index: 227910 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.3863. Min Act: -0.0000

Data Index: 420502 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.3883. Min Act: -0.0000

Data Index: 1144607 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.3208. Min Act: -0.0000

Data Index: 123533 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.2738. Min Act: -0.0000

Data Index: 484922 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.3389. Min Act: -0.0000

Data Index: 208068 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.2819. Min Act: -0.0001

Data Index: 1224912 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1047487 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 2.0864. Min Range: -2.0864

Max Act: 0.9851. Min Act: -0.0000

Data Index: 925620 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.0389. Min Act: -0.0000

Data Index: 831535 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.4303. Min Act: -0.0001

Data Index: 777192 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.2201. Min Act: -0.0001

Data Index: 373778 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.3311. Min Act: -0.0000

Data Index: 445523 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.0612. Min Act: -0.0000

Data Index: 477270 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.1172. Min Act: -0.0000

Data Index: 548338 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.1044. Min Act: -0.0000

Data Index: 565968 (C4 (Web Text))

Max Activating Token Index: 61