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

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

Neuron 725 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.1610. Min Act: -0.0000

Data Index: 1080400 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.3131. Min Act: -0.0000

Data Index: 950177 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.1539. Min Act: -0.0000

Data Index: 330456 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.0343. Min Act: -0.0000

Data Index: 65325 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.3763. Min Act: -0.0000

Data Index: 79835 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.1329. Min Act: -0.0000

Data Index: 43812 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.1258. Min Act: -0.0000

Data Index: 50899 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.1154. Min Act: -0.0000

Data Index: 1189788 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.1058. Min Act: -0.0000

Data Index: 727360 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.0791. Min Act: -0.0000

Data Index: 401814 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 2.3763. Min Range: -2.3763

Max Act: 1.9623. Min Act: -0.0000

Data Index: 1027994 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 2.3763. Min Range: -2.3763

Max Act: 1.9536. Min Act: -0.0000

Data Index: 450503 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.0895. Min Act: -0.0000

Data Index: 717361 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 2.3763. Min Range: -2.3763

Max Act: 1.9458. Min Act: -0.0000

Data Index: 877141 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 2.3763. Min Range: -2.3763

Max Act: 2.0234. Min Act: -0.0000

Data Index: 1284727 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 2.3763. Min Range: -2.3763

Max Act: 1.7993. Min Act: -0.0000

Data Index: 240016 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 2.3763. Min Range: -2.3763

Max Act: 1.9071. Min Act: -0.0000

Data Index: 1145255 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 2.3763. Min Range: -2.3763

Max Act: 1.7723. Min Act: -0.0000

Data Index: 985094 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 2.3763. Min Range: -2.3763

Max Act: 1.8571. Min Act: -0.0000

Data Index: 1355674 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 2.3763. Min Range: -2.3763

Max Act: 1.9137. Min Act: -0.0000

Data Index: 825816 (C4 (Web Text))

Max Activating Token Index: 652