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

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

Neuron 1795 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: 0.4962. Min Range: -0.4962

Max Act: 0.4962. Min Act: -0.0000

Data Index: 692341 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4820. Min Act: -0.0000

Data Index: 449777 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1284844 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1047653 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4107. Min Act: -0.0001

Data Index: 1040824 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4227. Min Act: -0.0000

Data Index: 59120 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4075. Min Act: -0.0001

Data Index: 397451 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4034. Min Act: -0.0000

Data Index: 245049 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4043. Min Act: -0.0001

Data Index: 323017 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1294841 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4086. Min Act: -0.0000

Data Index: 101505 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3834. Min Act: -0.0000

Data Index: 664681 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1238916 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3825. Min Act: -0.0000

Data Index: 304130 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1207288 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3886. Min Act: -0.0001

Data Index: 1098870 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3682. Min Act: -0.0000

Data Index: 555271 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3429. Min Act: -0.0001

Data Index: 735430 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1260445 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.4962. Min Range: -0.4962

Max Act: 0.3656. Min Act: -0.0000

Data Index: 13643 (C4 (Web Text))

Max Activating Token Index: 780