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

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

Neuron 972 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: 2.7521. Min Range: -2.7521

Max Act: 2.7521. Min Act: -0.0000

Data Index: 7798 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.4152. Min Act: -0.0000

Data Index: 99268 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.3709. Min Act: -0.0000

Data Index: 734361 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.2712. Min Act: -0.0000

Data Index: 818287 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.4121. Min Act: -0.0000

Data Index: 1151922 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.4050. Min Act: -0.0000

Data Index: 424075 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.4878. Min Act: -0.0000

Data Index: 1314743 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.2406. Min Act: -0.0000

Data Index: 292023 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.2240. Min Act: -0.0000

Data Index: 779924 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.3337. Min Act: -0.0000

Data Index: 645631 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.3198. Min Act: -0.0000

Data Index: 675984 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.2998. Min Act: -0.0000

Data Index: 403390 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.1403. Min Act: -0.0000

Data Index: 584642 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.2294. Min Act: -0.0000

Data Index: 80602 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.2452. Min Act: -0.0000

Data Index: 373618 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.1061. Min Act: -0.0000

Data Index: 915283 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.3656. Min Act: -0.0000

Data Index: 1190463 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.0987. Min Act: -0.0000

Data Index: 1151322 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.2069. Min Act: -0.0000

Data Index: 298835 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 2.7521. Min Range: -2.7521

Max Act: 2.2056. Min Act: -0.0000

Data Index: 1161106 (C4 (Web Text))

Max Activating Token Index: 166