Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 280 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0033. Min Act: -0.0006

Data Index: 1221230 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1154593 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0006

Data Index: 878033 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0005

Data Index: 96586 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0027. Min Act: -0.0005

Data Index: 1174656 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0027. Min Act: -0.0005

Data Index: 23931 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0005

Data Index: 1279623 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0005

Data Index: 781556 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0005

Data Index: 307266 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0026. Min Act: -0.0006

Data Index: 1117169 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0005

Data Index: 1354779 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0005

Data Index: 1492654 (Python Code)

Max Activating Token Index: 420

Text #12

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0005

Data Index: 803437 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0005

Data Index: 686964 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0025. Min Act: -0.0005

Data Index: 674207 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0024. Min Act: -0.0006

Data Index: 1113785 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0024. Min Act: -0.0005

Data Index: 252559 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0023. Min Act: -0.0005

Data Index: 731252 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0024. Min Act: -0.0005

Data Index: 280868 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0023. Min Act: -0.0005

Data Index: 892648 (C4 (Web Text))

Max Activating Token Index: 971