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

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

Neuron 4163 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.7980. Min Act: -0.0001

Data Index: 170785 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.4935. Min Act: -0.0001

Data Index: 625740 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.4848. Min Act: -0.0001

Data Index: 81780 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.2198. Min Act: -0.0001

Data Index: 608490 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 1.7980. Min Range: -1.7980

Max Act: 1.0715. Min Act: -0.0001

Data Index: 599245 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.9352. Min Act: -0.0001

Data Index: 1012388 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.9944. Min Act: -0.0001

Data Index: 1016704 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.8824. Min Act: -0.0001

Data Index: 298283 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1355617 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.8418. Min Act: -0.0001

Data Index: 46756 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.7917. Min Act: -0.0001

Data Index: 1355192 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.8708. Min Act: -0.0000

Data Index: 767287 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.7888. Min Act: -0.0000

Data Index: 218090 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.7803. Min Act: -0.0000

Data Index: 903388 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.6987. Min Act: -0.0000

Data Index: 124360 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.7459. Min Act: -0.0001

Data Index: 1306503 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.7367. Min Act: -0.0001

Data Index: 880947 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.7202. Min Act: -0.0000

Data Index: 673685 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1150858 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 1.7980. Min Range: -1.7980

Max Act: 0.7158. Min Act: -0.0000

Data Index: 441094 (C4 (Web Text))

Max Activating Token Index: 320