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

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

Neuron 1894 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3041. Min Act: -0.0000

Data Index: 438640 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1339994 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2956. Min Act: -0.0000

Data Index: 610419 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2876. Min Act: 0.0000

Data Index: 297298 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1351408 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2939. Min Act: -0.0000

Data Index: 681336 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3007. Min Act: -0.0000

Data Index: 213893 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1168581 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2745. Min Act: 0.0000

Data Index: 660901 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1223738 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2695. Min Act: 0.0000

Data Index: 968595 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2730. Min Act: -0.0000

Data Index: 546191 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2590. Min Act: 0.0000

Data Index: 1035448 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2486. Min Act: -0.0000

Data Index: 806730 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1173066 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2563. Min Act: -0.0000

Data Index: 990462 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2456. Min Act: -0.0000

Data Index: 816781 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2493. Min Act: -0.0000

Data Index: 523034 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2361. Min Act: -0.0000

Data Index: 320636 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2434. Min Act: -0.0000

Data Index: 676200 (C4 (Web Text))

Max Activating Token Index: 259