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

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

Neuron 2725 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: 0.3187. Min Range: -0.3187

Max Act: 0.3187. Min Act: -0.0001

Data Index: 407631 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2695. Min Act: -0.0001

Data Index: 1078897 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2648. Min Act: -0.0001

Data Index: 944823 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2423. Min Act: -0.0001

Data Index: 624804 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2172. Min Act: -0.0001

Data Index: 843569 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2121. Min Act: -0.0001

Data Index: 44383 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2029. Min Act: -0.0001

Data Index: 478196 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2069. Min Act: -0.0001

Data Index: 586420 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2350. Min Act: -0.0001

Data Index: 1121499 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1030498 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2143. Min Act: -0.0001

Data Index: 1114838 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2173. Min Act: -0.0001

Data Index: 537042 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2177. Min Act: -0.0001

Data Index: 1006851 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1879. Min Act: -0.0001

Data Index: 169004 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2023. Min Act: -0.0001

Data Index: 412920 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1854. Min Act: -0.0001

Data Index: 243868 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1875. Min Act: -0.0001

Data Index: 68284 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1959. Min Act: -0.0001

Data Index: 544807 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1752. Min Act: -0.0001

Data Index: 590168 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.1815. Min Act: -0.0001

Data Index: 442775 (C4 (Web Text))

Max Activating Token Index: 653