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

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

Neuron 2832 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: 0.3069. Min Range: -0.3069

Max Act: 0.3069. Min Act: -0.0000

Data Index: 788043 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2902. Min Act: -0.0000

Data Index: 319284 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1210745 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2668. Min Act: -0.0000

Data Index: 447595 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2619. Min Act: -0.0000

Data Index: 729504 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2576. Min Act: -0.0000

Data Index: 356544 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1126934 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2323. Min Act: -0.0000

Data Index: 881916 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2251. Min Act: -0.0000

Data Index: 120984 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2153. Min Act: -0.0000

Data Index: 732259 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2158. Min Act: -0.0000

Data Index: 941341 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2447. Min Act: -0.0000

Data Index: 630679 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2205. Min Act: -0.0000

Data Index: 972425 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2255. Min Act: -0.0000

Data Index: 976753 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1202105 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2154. Min Act: -0.0000

Data Index: 214465 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2219. Min Act: -0.0000

Data Index: 530237 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2204. Min Act: -0.0000

Data Index: 902978 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2125. Min Act: -0.0000

Data Index: 787770 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2173. Min Act: -0.0000

Data Index: 407204 (C4 (Web Text))

Max Activating Token Index: 1013