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

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

Neuron 3654 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: 5.6185. Min Range: -5.6185

Max Act: 5.6185. Min Act: -0.0001

Data Index: 553023 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.4428. Min Act: -0.0001

Data Index: 77792 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.3141. Min Act: -0.0001

Data Index: 105107 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.2380. Min Act: -0.0001

Data Index: 1300794 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.1982. Min Act: -0.0001

Data Index: 890224 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.1421. Min Act: -0.0001

Data Index: 1125045 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.1438. Min Act: -0.0001

Data Index: 406591 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 5.6185. Min Range: -5.6185

Max Act: 4.9580. Min Act: -0.0001

Data Index: 1106670 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.0781. Min Act: -0.0001

Data Index: 324228 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.0907. Min Act: -0.0001

Data Index: 629777 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 5.6185. Min Range: -5.6185

Max Act: 4.9144. Min Act: -0.0001

Data Index: 364284 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.0471. Min Act: -0.0001

Data Index: 668671 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.0355. Min Act: -0.0001

Data Index: 223945 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 5.6185. Min Range: -5.6185

Max Act: 4.8555. Min Act: -0.0001

Data Index: 1272606 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.0430. Min Act: -0.0001

Data Index: 1222617 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.0091. Min Act: -0.0001

Data Index: 997879 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 5.6185. Min Range: -5.6185

Max Act: 5.0274. Min Act: -0.0001

Data Index: 984437 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 5.6185. Min Range: -5.6185

Max Act: 4.7935. Min Act: -0.0001

Data Index: 1250037 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 5.6185. Min Range: -5.6185

Max Act: 4.9810. Min Act: -0.0001

Data Index: 1228510 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 5.6185. Min Range: -5.6185

Max Act: 4.9635. Min Act: -0.0001

Data Index: 327792 (C4 (Web Text))

Max Activating Token Index: 460