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

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

Neuron 4878 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2209. Min Range: -3.2209

Max Act: 3.2209. Min Act: -0.0001

Data Index: 1180572 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.8836. Min Act: -0.0001

Data Index: 29980 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.7173. Min Act: -0.0001

Data Index: 424624 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.7068. Min Act: -0.0001

Data Index: 1259633 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.7826. Min Act: -0.0001

Data Index: 654273 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.7707. Min Act: -0.0001

Data Index: 1085145 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.5456. Min Act: -0.0001

Data Index: 416621 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.4799. Min Act: -0.0001

Data Index: 487122 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.6123. Min Act: -0.0001

Data Index: 1348358 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.4813. Min Act: -0.0001

Data Index: 285968 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.9545. Min Act: -0.0001

Data Index: 228727 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.7098. Min Act: -0.0001

Data Index: 905710 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.5809. Min Act: -0.0001

Data Index: 1164392 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.6773. Min Act: -0.0001

Data Index: 1031579 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.4934. Min Act: -0.0001

Data Index: 329168 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.2685. Min Act: -0.0001

Data Index: 793774 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.1401. Min Act: -0.0001

Data Index: 476057 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.3207. Min Act: -0.0001

Data Index: 768124 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.3809. Min Act: -0.0001

Data Index: 65022 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 3.2209. Min Range: -3.2209

Max Act: 2.3873. Min Act: -0.0001

Data Index: 352984 (C4 (Web Text))

Max Activating Token Index: 598