Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2256 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1287408 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5842. Min Act: -0.0000

Data Index: 480291 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1235133 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1357894 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5167. Min Act: -0.0000

Data Index: 658328 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5366. Min Act: -0.0000

Data Index: 342890 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5311. Min Act: -0.0000

Data Index: 254246 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5334. Min Act: -0.0000

Data Index: 665844 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5363. Min Act: -0.0000

Data Index: 732715 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5314. Min Act: -0.0000

Data Index: 393832 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1326940 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4634. Min Act: -0.0000

Data Index: 128526 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4926. Min Act: -0.0000

Data Index: 985486 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4676. Min Act: -0.0000

Data Index: 483060 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4997. Min Act: -0.0000

Data Index: 233268 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1209648 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1057976 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4532. Min Act: -0.0000

Data Index: 49768 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4618. Min Act: -0.0000

Data Index: 43146 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.5842. Min Range: -0.5842

Max Act: 0.4311. Min Act: -0.0000

Data Index: 956053 (C4 (Web Text))

Max Activating Token Index: 223