Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5163 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1576. Min Range: -2.1576

Max Act: 2.1576. Min Act: -0.0000

Data Index: 1514461 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.8773. Min Act: -0.0000

Data Index: 249295 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.5758. Min Act: -0.0000

Data Index: 519957 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.6097. Min Act: -0.0000

Data Index: 775961 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.5740. Min Act: -0.0000

Data Index: 737283 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.7404. Min Act: -0.0000

Data Index: 1412410 (Python Code)

Max Activating Token Index: 501

Text #6

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.5717. Min Act: -0.0000

Data Index: 725692 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.7424. Min Act: -0.0000

Data Index: 1637075 (Python Code)

Max Activating Token Index: 578

Text #8

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.6377. Min Act: -0.0000

Data Index: 169688 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.6597. Min Act: -0.0000

Data Index: 1096081 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.4603. Min Act: -0.0000

Data Index: 372800 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.4546. Min Act: -0.0000

Data Index: 144093 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.5352. Min Act: -0.0000

Data Index: 241905 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.4483. Min Act: -0.0000

Data Index: 1201363 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.6229. Min Act: -0.0000

Data Index: 532170 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.4485. Min Act: -0.0000

Data Index: 377593 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.3594. Min Act: -0.0000

Data Index: 1121047 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.4285. Min Act: -0.0000

Data Index: 540026 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.5017. Min Act: -0.0000

Data Index: 79421 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 2.1576. Min Range: -2.1576

Max Act: 1.4377. Min Act: -0.0000

Data Index: 966775 (C4 (Web Text))

Max Activating Token Index: 775