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

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

Neuron 1442 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: 0.4872. Min Range: -0.4872

Max Act: 0.4872. Min Act: -0.0000

Data Index: 414066 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4489. Min Act: -0.0000

Data Index: 863905 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1007603 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1303486 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4197. Min Act: -0.0000

Data Index: 754560 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1257877 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1316868 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3591. Min Act: -0.0000

Data Index: 278814 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3854. Min Act: -0.0000

Data Index: 393483 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3697. Min Act: -0.0000

Data Index: 787822 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3564. Min Act: -0.0000

Data Index: 464223 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3682. Min Act: -0.0000

Data Index: 722695 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3469. Min Act: -0.0000

Data Index: 508148 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1290475 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3609. Min Act: -0.0000

Data Index: 14722 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3366. Min Act: -0.0000

Data Index: 509101 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1181261 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3288. Min Act: -0.0000

Data Index: 273087 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1026202 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3242. Min Act: -0.0000

Data Index: 972446 (C4 (Web Text))

Max Activating Token Index: 66