Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3722 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.4471. Min Act: -0.0000

Data Index: 573217 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.4440. Min Act: -0.0000

Data Index: 224352 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.3233. Min Act: -0.0000

Data Index: 1046172 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1560. Min Act: -0.0000

Data Index: 80370 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.2262. Min Act: -0.0000

Data Index: 89070 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.2794. Min Act: -0.0000

Data Index: 408245 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.2385. Min Act: -0.0000

Data Index: 611597 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1677. Min Act: -0.0000

Data Index: 918335 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0979. Min Act: -0.0000

Data Index: 946700 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1638. Min Act: -0.0000

Data Index: 363008 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1302. Min Act: -0.0000

Data Index: 668021 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1121. Min Act: -0.0000

Data Index: 1025630 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1241604 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1070. Min Act: -0.0000

Data Index: 1121930 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1073. Min Act: -0.0000

Data Index: 272764 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0722. Min Act: -0.0000

Data Index: 539570 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1205. Min Act: -0.0000

Data Index: 87107 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0486. Min Act: -0.0000

Data Index: 1159072 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1010. Min Act: -0.0000

Data Index: 385042 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.4471. Min Range: -1.4471

Max Act: 0.9781. Min Act: -0.0000

Data Index: 278151 (C4 (Web Text))

Max Activating Token Index: 589