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

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

Neuron 3378 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5077. Min Range: -2.5077

Max Act: 2.5077. Min Act: -0.0000

Data Index: 335288 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 2.5077. Min Range: -2.5077

Max Act: 2.3122. Min Act: -0.0000

Data Index: 605503 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 2.5077. Min Range: -2.5077

Max Act: 2.2985. Min Act: -0.0000

Data Index: 1236170 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.8927. Min Act: -0.0000

Data Index: 525447 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.9117. Min Act: -0.0000

Data Index: 1026801 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.8675. Min Act: -0.0000

Data Index: 1328150 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 2.5077. Min Range: -2.5077

Max Act: 2.0705. Min Act: -0.0000

Data Index: 947934 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.9861. Min Act: -0.0000

Data Index: 879877 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 2.5077. Min Range: -2.5077

Max Act: 2.0594. Min Act: -0.0000

Data Index: 825682 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 2.5077. Min Range: -2.5077

Max Act: 2.0346. Min Act: -0.0000

Data Index: 1300607 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.9237. Min Act: -0.0000

Data Index: 711748 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.8229. Min Act: -0.0000

Data Index: 1086542 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.7965. Min Act: -0.0000

Data Index: 560638 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.7414. Min Act: -0.0000

Data Index: 588380 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.7337. Min Act: -0.0000

Data Index: 940269 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.7094. Min Act: -0.0000

Data Index: 946928 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.6943. Min Act: -0.0000

Data Index: 1294996 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.6525. Min Act: -0.0000

Data Index: 368304 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.7610. Min Act: -0.0000

Data Index: 398135 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 2.5077. Min Range: -2.5077

Max Act: 1.7188. Min Act: -0.0000

Data Index: 398131 (C4 (Web Text))

Max Activating Token Index: 231