Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 773 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.6170. Min Act: -0.0001

Data Index: 901983 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.3662. Min Act: -0.0001

Data Index: 150407 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.4591. Min Act: -0.0001

Data Index: 1150197 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.2862. Min Act: -0.0001

Data Index: 43257 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.2264. Min Act: -0.0000

Data Index: 160021 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.1389. Min Act: -0.0001

Data Index: 269657 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.0545. Min Act: -0.0001

Data Index: 816524 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.0866. Min Act: -0.0000

Data Index: 207689 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 1.6170. Min Range: -1.6170

Max Act: 0.9280. Min Act: -0.0001

Data Index: 379070 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.6170. Min Range: -1.6170

Max Act: 0.9358. Min Act: -0.0001

Data Index: 379304 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.0259. Min Act: -0.0001

Data Index: 1001153 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 1.6170. Min Range: -1.6170

Max Act: 0.9445. Min Act: -0.0001

Data Index: 1227602 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.6170. Min Range: -1.6170

Max Act: 0.7783. Min Act: -0.0001

Data Index: 1036843 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.6170. Min Range: -1.6170

Max Act: 0.8385. Min Act: -0.0001

Data Index: 213161 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 1.6170. Min Range: -1.6170

Max Act: 0.9208. Min Act: -0.0001

Data Index: 677687 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.0341. Min Act: -0.0001

Data Index: 1179162 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 1.6170. Min Range: -1.6170

Max Act: 0.9354. Min Act: -0.0001

Data Index: 914404 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.6170. Min Range: -1.6170

Max Act: 1.1589. Min Act: -0.0001

Data Index: 1014276 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.6170. Min Range: -1.6170

Max Act: 0.8343. Min Act: -0.0000

Data Index: 207289 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 1.6170. Min Range: -1.6170

Max Act: 0.9157. Min Act: -0.0001

Data Index: 601881 (C4 (Web Text))

Max Activating Token Index: 90