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

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

Neuron 3697 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.3111. Min Act: -0.0001

Data Index: 429400 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.3300. Min Act: -0.0001

Data Index: 575794 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2899. Min Act: -0.0000

Data Index: 65966 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2935. Min Act: -0.0001

Data Index: 994509 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1329980 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2539. Min Act: -0.0000

Data Index: 84156 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2378. Min Act: -0.0000

Data Index: 746996 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2573. Min Act: -0.0000

Data Index: 315947 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2441. Min Act: -0.0000

Data Index: 826569 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2347. Min Act: -0.0000

Data Index: 844239 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2324. Min Act: -0.0001

Data Index: 269698 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2225. Min Act: -0.0000

Data Index: 687111 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2288. Min Act: -0.0001

Data Index: 1343472 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2284. Min Act: -0.0001

Data Index: 402940 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2172. Min Act: -0.0000

Data Index: 412516 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2207. Min Act: -0.0000

Data Index: 481071 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2272. Min Act: -0.0000

Data Index: 699761 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1162405 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2262. Min Act: -0.0001

Data Index: 1007840 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.3300. Min Range: -0.3300

Max Act: 0.2164. Min Act: -0.0001

Data Index: 506860 (C4 (Web Text))

Max Activating Token Index: 298