Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1979 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.2743. Min Range: -4.2743

Max Act: 4.1719. Min Act: -0.0001

Data Index: 53886 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 4.2743. Min Range: -4.2743

Max Act: 4.2743. Min Act: -0.0001

Data Index: 1285087 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.8772. Min Act: -0.0000

Data Index: 624899 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 4.2743. Min Range: -4.2743

Max Act: 4.0147. Min Act: -0.0001

Data Index: 209769 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.9325. Min Act: -0.0001

Data Index: 882191 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.7847. Min Act: -0.0000

Data Index: 61158 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.5817. Min Act: -0.0000

Data Index: 751266 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.6899. Min Act: -0.0001

Data Index: 833325 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.6739. Min Act: -0.0000

Data Index: 29090 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.4237. Min Act: -0.0001

Data Index: 1288795 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.2450. Min Act: -0.0001

Data Index: 189027 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.3915. Min Act: -0.0001

Data Index: 738155 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.0580. Min Act: -0.0001

Data Index: 598804 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.1364. Min Act: -0.0001

Data Index: 396832 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 4.2743. Min Range: -4.2743

Max Act: 2.9916. Min Act: -0.0000

Data Index: 387199 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.2823. Min Act: -0.0000

Data Index: 1354994 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 4.2743. Min Range: -4.2743

Max Act: 2.9895. Min Act: -0.0000

Data Index: 1067640 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 4.2743. Min Range: -4.2743

Max Act: 2.9285. Min Act: -0.0001

Data Index: 910255 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 4.2743. Min Range: -4.2743

Max Act: 3.0602. Min Act: -0.0001

Data Index: 12492 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 4.2743. Min Range: -4.2743

Max Act: 2.9100. Min Act: -0.0000

Data Index: 1072817 (C4 (Web Text))

Max Activating Token Index: 302