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

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

Neuron 1343 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.4063. Min Act: -0.0000

Data Index: 1231977 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.3737. Min Act: -0.0000

Data Index: 1138432 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.2497. Min Act: -0.0000

Data Index: 1298916 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.1175. Min Act: -0.0000

Data Index: 463328 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.9586. Min Act: -0.0000

Data Index: 40202 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.0647. Min Act: -0.0000

Data Index: 659134 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.1972. Min Act: -0.0000

Data Index: 966103 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.7648. Min Act: -0.0000

Data Index: 969591 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.9419. Min Act: -0.0000

Data Index: 650661 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.8079. Min Act: -0.0000

Data Index: 13420 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.7683. Min Act: -0.0000

Data Index: 475068 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.9903. Min Act: -0.0000

Data Index: 482000 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.6599. Min Act: -0.0000

Data Index: 1032594 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.6485. Min Act: -0.0000

Data Index: 1236378 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.5173. Min Act: -0.0000

Data Index: 135949 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.7278. Min Act: -0.0000

Data Index: 998508 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.6435. Min Act: -0.0000

Data Index: 117625 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.6064. Min Act: -0.0000

Data Index: 41668 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.4715. Min Act: -0.0000

Data Index: 504081 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 2.4063. Min Range: -2.4063

Max Act: 1.5035. Min Act: -0.0000

Data Index: 878212 (C4 (Web Text))

Max Activating Token Index: 771