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

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

Neuron 4028 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.1034. Min Act: -0.0002

Data Index: 485637 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.0329. Min Act: -0.0002

Data Index: 1262773 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9498. Min Act: -0.0002

Data Index: 193308 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.0279. Min Act: -0.0002

Data Index: 184391 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.0531. Min Act: -0.0002

Data Index: 1095409 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.0428. Min Act: -0.0002

Data Index: 865915 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8472. Min Act: -0.0002

Data Index: 1064521 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.1009. Min Act: -0.0002

Data Index: 222102 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9374. Min Act: -0.0002

Data Index: 36398 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8008. Min Act: -0.0002

Data Index: 1129443 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8994. Min Act: -0.0002

Data Index: 38062 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9559. Min Act: -0.0002

Data Index: 472330 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.0491. Min Act: -0.0002

Data Index: 121735 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9761. Min Act: -0.0002

Data Index: 10349 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8969. Min Act: -0.0002

Data Index: 987493 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9357. Min Act: -0.0002

Data Index: 70203 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7477. Min Act: -0.0002

Data Index: 177047 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9324. Min Act: -0.0002

Data Index: 704315 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.0554. Min Act: -0.0002

Data Index: 535660 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.1034. Min Range: -1.1034

Max Act: 1.0466. Min Act: -0.0002

Data Index: 788796 (C4 (Web Text))

Max Activating Token Index: 118