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

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

Neuron 5043 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.2721. Min Act: -0.0001

Data Index: 876182 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.4079. Min Act: -0.0001

Data Index: 330038 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.2825. Min Act: -0.0001

Data Index: 504099 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.3600. Min Act: -0.0001

Data Index: 283866 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.2424. Min Act: -0.0001

Data Index: 575956 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.2134. Min Act: -0.0001

Data Index: 331079 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.3054. Min Act: -0.0001

Data Index: 81891 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.3650. Min Act: -0.0001

Data Index: 107138 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.2035. Min Act: -0.0001

Data Index: 119277 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.2268. Min Act: -0.0001

Data Index: 756047 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.1522. Min Act: -0.0001

Data Index: 271419 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.3506. Min Act: -0.0001

Data Index: 907992 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.4259. Min Act: -0.0001

Data Index: 624888 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.0837. Min Act: -0.0001

Data Index: 887282 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.1962. Min Act: -0.0001

Data Index: 986142 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.1285. Min Act: -0.0001

Data Index: 170003 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.1537. Min Act: -0.0001

Data Index: 834904 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.0920. Min Act: -0.0001

Data Index: 110285 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.1554. Min Act: -0.0001

Data Index: 290824 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.4259. Min Range: -1.4259

Max Act: 1.0706. Min Act: -0.0001

Data Index: 1101527 (C4 (Web Text))

Max Activating Token Index: 262