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

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

Neuron 3547 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0165. Min Range: -2.0165

Max Act: 2.0165. Min Act: -0.0001

Data Index: 57806 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.7240. Min Act: -0.0001

Data Index: 910805 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.5682. Min Act: -0.0001

Data Index: 1338576 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.6564. Min Act: -0.0000

Data Index: 433748 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.5775. Min Act: -0.0001

Data Index: 119742 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.5518. Min Act: -0.0000

Data Index: 439923 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.5427. Min Act: -0.0000

Data Index: 122164 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1078177 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.4494. Min Act: -0.0001

Data Index: 1242770 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.4447. Min Act: -0.0000

Data Index: 108767 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.4518. Min Act: -0.0000

Data Index: 1243927 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.4493. Min Act: -0.0001

Data Index: 815330 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.3827. Min Act: -0.0000

Data Index: 878939 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.3680. Min Act: -0.0000

Data Index: 640439 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.3980. Min Act: -0.0001

Data Index: 1302888 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.4417. Min Act: -0.0000

Data Index: 768599 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.3189. Min Act: -0.0001

Data Index: 1079172 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.3815. Min Act: -0.0000

Data Index: 605753 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.3607. Min Act: -0.0000

Data Index: 232587 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 2.0165. Min Range: -2.0165

Max Act: 1.3077. Min Act: -0.0001

Data Index: 481633 (C4 (Web Text))

Max Activating Token Index: 870