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

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

Neuron 644 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: 2.4267. Min Range: -2.4267

Max Act: 2.4267. Min Act: -0.0000

Data Index: 642010 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 2.4267. Min Range: -2.4267

Max Act: 2.3906. Min Act: -0.0000

Data Index: 920872 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 2.4267. Min Range: -2.4267

Max Act: 2.3355. Min Act: -0.0000

Data Index: 501966 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 2.4267. Min Range: -2.4267

Max Act: 2.0305. Min Act: -0.0000

Data Index: 40503 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.9466. Min Act: -0.0000

Data Index: 541052 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.8936. Min Act: -0.0000

Data Index: 1043326 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 2.4267. Min Range: -2.4267

Max Act: 2.0724. Min Act: -0.0000

Data Index: 1163430 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.9395. Min Act: -0.0000

Data Index: 608878 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.9736. Min Act: -0.0000

Data Index: 982094 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.5574. Min Act: -0.0000

Data Index: 966410 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.4679. Min Act: -0.0000

Data Index: 947657 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.5601. Min Act: -0.0000

Data Index: 776321 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.4605. Min Act: -0.0000

Data Index: 1213230 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1229948 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.2543. Min Act: -0.0000

Data Index: 221885 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.2486. Min Act: 0.0000

Data Index: 156213 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.1330. Min Act: -0.0000

Data Index: 133772 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.2279. Min Act: -0.0000

Data Index: 246514 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1094711 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 2.4267. Min Range: -2.4267

Max Act: 1.0871. Min Act: -0.0000

Data Index: 869567 (C4 (Web Text))

Max Activating Token Index: 747