Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 436 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2688. Min Act: -0.0001

Data Index: 1417 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2606. Min Act: -0.0000

Data Index: 913549 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1356084 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2349. Min Act: -0.0000

Data Index: 521198 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2325. Min Act: -0.0001

Data Index: 855209 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2455. Min Act: -0.0001

Data Index: 316745 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2198. Min Act: -0.0000

Data Index: 985663 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2161. Min Act: -0.0000

Data Index: 738448 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2173. Min Act: -0.0000

Data Index: 234220 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2217. Min Act: -0.0001

Data Index: 178799 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2149. Min Act: -0.0001

Data Index: 681014 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2135. Min Act: -0.0000

Data Index: 36254 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1987. Min Act: -0.0001

Data Index: 107958 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2041. Min Act: -0.0001

Data Index: 749484 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1068265 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1949. Min Act: -0.0001

Data Index: 263626 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2011. Min Act: -0.0000

Data Index: 11500 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1952. Min Act: -0.0001

Data Index: 871859 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1942. Min Act: -0.0000

Data Index: 983511 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1961. Min Act: -0.0001

Data Index: 525346 (C4 (Web Text))

Max Activating Token Index: 505