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

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

Neuron 204 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2622. Min Act: -0.0001

Data Index: 285328 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2616. Min Act: -0.0001

Data Index: 506094 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2567. Min Act: -0.0001

Data Index: 1189988 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1129622 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2432. Min Act: -0.0001

Data Index: 917166 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2210. Min Act: -0.0001

Data Index: 83234 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2257. Min Act: -0.0001

Data Index: 43295 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2204. Min Act: -0.0000

Data Index: 188001 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2104. Min Act: -0.0001

Data Index: 936838 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2169. Min Act: -0.0001

Data Index: 576801 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1947. Min Act: -0.0001

Data Index: 929971 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2124. Min Act: -0.0001

Data Index: 311799 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1848. Min Act: -0.0001

Data Index: 19505 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1355048 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1001834 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2096. Min Act: -0.0000

Data Index: 723354 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1955. Min Act: -0.0001

Data Index: 667018 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1782. Min Act: -0.0000

Data Index: 792271 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1801. Min Act: -0.0001

Data Index: 591565 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1878. Min Act: -0.0001

Data Index: 733883 (C4 (Web Text))

Max Activating Token Index: 480