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

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

Neuron 2725 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0938. Min Range: -6.0938

Max Act: 6.0938. Min Act: -0.0000

Data Index: 1079975 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 6.0938. Min Range: -6.0938

Max Act: 5.1855. Min Act: -0.0000

Data Index: 189177 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.8287. Min Act: -0.0000

Data Index: 842258 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.5189. Min Act: -0.0000

Data Index: 280769 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.4669. Min Act: -0.0000

Data Index: 287829 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.2575. Min Act: -0.0000

Data Index: 1250097 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.4835. Min Act: -0.0000

Data Index: 598784 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.2717. Min Act: -0.0000

Data Index: 772958 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.5941. Min Act: -0.0000

Data Index: 226727 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.4872. Min Act: -0.0000

Data Index: 307827 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.1658. Min Act: -0.0000

Data Index: 1053495 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.0216. Min Act: -0.0001

Data Index: 298810 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.3062. Min Act: -0.0000

Data Index: 1243168 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.4668. Min Act: -0.0000

Data Index: 873270 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 6.0938. Min Range: -6.0938

Max Act: 3.9573. Min Act: -0.0000

Data Index: 1199196 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.1128. Min Act: -0.0000

Data Index: 542828 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 6.0938. Min Range: -6.0938

Max Act: 4.0774. Min Act: -0.0000

Data Index: 404431 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 6.0938. Min Range: -6.0938

Max Act: 3.9789. Min Act: -0.0000

Data Index: 515498 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 6.0938. Min Range: -6.0938

Max Act: 3.8139. Min Act: -0.0000

Data Index: 1144946 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 6.0938. Min Range: -6.0938

Max Act: 3.9309. Min Act: -0.0000

Data Index: 668038 (C4 (Web Text))

Max Activating Token Index: 938