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

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

Neuron 3609 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1247567 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1323. Min Act: -0.0001

Data Index: 827477 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1005693 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1255. Min Act: -0.0001

Data Index: 790730 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1289. Min Act: -0.0001

Data Index: 440287 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1193. Min Act: -0.0001

Data Index: 72698 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1227. Min Act: -0.0001

Data Index: 547324 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1213. Min Act: -0.0001

Data Index: 420784 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1345246 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1143. Min Act: -0.0001

Data Index: 366559 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1211. Min Act: -0.0001

Data Index: 158655 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1149. Min Act: -0.0001

Data Index: 577456 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1073. Min Act: -0.0001

Data Index: 499114 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1171. Min Act: -0.0001

Data Index: 149489 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1261. Min Act: -0.0001

Data Index: 443835 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1083. Min Act: -0.0001

Data Index: 533479 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1201745 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1041. Min Act: -0.0001

Data Index: 773270 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1174129 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1024. Min Act: -0.0001

Data Index: 725300 (C4 (Web Text))

Max Activating Token Index: 43