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

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

Neuron 4835 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1022197 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2492. Min Act: -0.0000

Data Index: 566934 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1882. Min Act: -0.0000

Data Index: 169006 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1691. Min Act: -0.0000

Data Index: 746992 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1848. Min Act: -0.0000

Data Index: 770054 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1644. Min Act: -0.0000

Data Index: 798086 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1593. Min Act: -0.0000

Data Index: 794168 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1721. Min Act: -0.0000

Data Index: 945851 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1720. Min Act: -0.0000

Data Index: 646479 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1083638 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1710. Min Act: -0.0000

Data Index: 209974 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1909. Min Act: -0.0000

Data Index: 748180 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1352. Min Act: -0.0000

Data Index: 888708 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1397. Min Act: -0.0000

Data Index: 485117 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1638. Min Act: -0.0000

Data Index: 431279 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1074796 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1434. Min Act: -0.0000

Data Index: 856022 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1467. Min Act: -0.0000

Data Index: 546164 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1471. Min Act: -0.0000

Data Index: 436283 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1350. Min Act: -0.0000

Data Index: 988959 (C4 (Web Text))

Max Activating Token Index: 666