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

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

Neuron 2129 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: 0.3025. Min Range: -0.3025

Max Act: 0.2832. Min Act: -0.0001

Data Index: 145088 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1055759 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2598. Min Act: -0.0000

Data Index: 861971 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2383. Min Act: -0.0000

Data Index: 426506 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1280000 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2388. Min Act: -0.0000

Data Index: 95570 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1225336 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2457. Min Act: -0.0001

Data Index: 290201 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2393. Min Act: -0.0001

Data Index: 1159426 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2265. Min Act: -0.0000

Data Index: 443172 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2276. Min Act: -0.0001

Data Index: 777285 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2234. Min Act: -0.0001

Data Index: 430301 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1172991 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2272. Min Act: -0.0001

Data Index: 1125461 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2138. Min Act: -0.0001

Data Index: 793016 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2257. Min Act: -0.0001

Data Index: 947930 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2082. Min Act: -0.0001

Data Index: 633666 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2171. Min Act: -0.0000

Data Index: 706539 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2616. Min Act: -0.0000

Data Index: 207442 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2138. Min Act: -0.0001

Data Index: 759262 (C4 (Web Text))

Max Activating Token Index: 110