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

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

Neuron 826 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.6472. Min Act: -0.0000

Data Index: 286764 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4596. Min Act: -0.0000

Data Index: 237497 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1073453 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.3353. Min Act: -0.0000

Data Index: 866140 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1137078 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.2134. Min Act: -0.0000

Data Index: 135565 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.2110. Min Act: -0.0000

Data Index: 216569 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1247457 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1726. Min Act: -0.0000

Data Index: 589918 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1190812 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1567. Min Act: -0.0000

Data Index: 278824 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1156338 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1549. Min Act: -0.0000

Data Index: 996241 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1569. Min Act: -0.0000

Data Index: 856263 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1458. Min Act: -0.0000

Data Index: 875750 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1150854 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1269521 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1485. Min Act: -0.0000

Data Index: 100321 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1262374 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.1501. Min Act: -0.0000

Data Index: 668706 (C4 (Web Text))

Max Activating Token Index: 543