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

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

Neuron 3999 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.6700. Min Act: -0.0000

Data Index: 605466 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.5092. Min Act: 0.0000

Data Index: 1198758 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.4690. Min Act: -0.0000

Data Index: 480597 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.3356. Min Act: -0.0000

Data Index: 789305 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.3059. Min Act: -0.0000

Data Index: 45243 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.2166. Min Act: -0.0000

Data Index: 262845 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.0794. Min Act: -0.0000

Data Index: 643751 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 2.6700. Min Range: -2.6700

Max Act: 1.9731. Min Act: -0.0000

Data Index: 1125054 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.2303. Min Act: -0.0000

Data Index: 708175 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.0761. Min Act: -0.0000

Data Index: 204174 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 2.6700. Min Range: -2.6700

Max Act: 1.9328. Min Act: -0.0000

Data Index: 645806 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.0393. Min Act: -0.0000

Data Index: 29904 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 2.6700. Min Range: -2.6700

Max Act: 2.0487. Min Act: -0.0000

Data Index: 1132506 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 2.6700. Min Range: -2.6700

Max Act: 1.9990. Min Act: 0.0000

Data Index: 936738 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 2.6700. Min Range: -2.6700

Max Act: 1.9912. Min Act: -0.0000

Data Index: 1222234 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 2.6700. Min Range: -2.6700

Max Act: 1.8843. Min Act: 0.0001

Data Index: 403500 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 2.6700. Min Range: -2.6700

Max Act: 1.9668. Min Act: -0.0000

Data Index: 229268 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 2.6700. Min Range: -2.6700

Max Act: 1.8460. Min Act: -0.0000

Data Index: 22721 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 2.6700. Min Range: -2.6700

Max Act: 1.9133. Min Act: -0.0000

Data Index: 385728 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 2.6700. Min Range: -2.6700

Max Act: 1.7598. Min Act: -0.0000

Data Index: 995488 (C4 (Web Text))

Max Activating Token Index: 207