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

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

Neuron 3937 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1074046 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.7171. Min Act: -0.0000

Data Index: 799088 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1585147 (Python Code)

Max Activating Token Index: 38

Text #3

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1031326 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1293183 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5813. Min Act: -0.0000

Data Index: 56607 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5793. Min Act: -0.0000

Data Index: 667627 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5602. Min Act: -0.0000

Data Index: 654783 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5352. Min Act: -0.0000

Data Index: 763241 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5309. Min Act: -0.0000

Data Index: 892087 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4857. Min Act: -0.0000

Data Index: 180448 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5144. Min Act: -0.0000

Data Index: 53532 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4875. Min Act: -0.0000

Data Index: 235453 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4847. Min Act: -0.0000

Data Index: 988747 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.5089. Min Act: -0.0000

Data Index: 661822 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1181720 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4638. Min Act: -0.0000

Data Index: 583559 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4338. Min Act: -0.0000

Data Index: 745841 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4458. Min Act: -0.0000

Data Index: 71780 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.7524. Min Range: -0.7524

Max Act: 0.4463. Min Act: -0.0000

Data Index: 98576 (C4 (Web Text))

Max Activating Token Index: 903