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

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

Neuron 126 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.5991. Min Act: -0.0002

Data Index: 241065 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.5158. Min Act: -0.0002

Data Index: 1291063 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.5332. Min Act: -0.0002

Data Index: 472527 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.5405. Min Act: -0.0002

Data Index: 1224430 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.5689. Min Act: -0.0002

Data Index: 261628 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.5057. Min Act: -0.0002

Data Index: 943621 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.5095. Min Act: -0.0002

Data Index: 109181 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4568. Min Act: -0.0002

Data Index: 1134175 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4875. Min Act: -0.0002

Data Index: 356011 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4521. Min Act: -0.0002

Data Index: 108404 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4424. Min Act: -0.0002

Data Index: 806641 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4413. Min Act: -0.0002

Data Index: 386076 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4505. Min Act: -0.0002

Data Index: 508027 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4103. Min Act: -0.0002

Data Index: 370363 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.3994. Min Act: -0.0002

Data Index: 15432 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4002. Min Act: -0.0002

Data Index: 866676 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.3744. Min Act: -0.0002

Data Index: 539266 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.3904. Min Act: -0.0002

Data Index: 1008868 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.3460. Min Act: -0.0002

Data Index: 910929 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 1.5991. Min Range: -1.5991

Max Act: 1.4107. Min Act: -0.0002

Data Index: 1100734 (C4 (Web Text))

Max Activating Token Index: 451