Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3166 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.3142. Min Act: -0.0001

Data Index: 904674 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2954. Min Act: -0.0000

Data Index: 9068 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2964. Min Act: -0.0001

Data Index: 371614 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2788. Min Act: -0.0001

Data Index: 1223362 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2752. Min Act: 0.0001

Data Index: 113022 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2723. Min Act: -0.0000

Data Index: 591415 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2685. Min Act: -0.0000

Data Index: 728000 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2678. Min Act: -0.0001

Data Index: 1170259 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2746. Min Act: -0.0000

Data Index: 199856 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2598. Min Act: -0.0001

Data Index: 756422 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2591. Min Act: 0.0000

Data Index: 454002 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2644. Min Act: 0.0000

Data Index: 647076 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1285807 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2617. Min Act: -0.0000

Data Index: 175813 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2600. Min Act: -0.0000

Data Index: 795070 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2492. Min Act: -0.0001

Data Index: 307294 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2557. Min Act: 0.0000

Data Index: 40128 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2498. Min Act: 0.0000

Data Index: 313763 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1281782 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1057801 (C4 (Web Text))

Max Activating Token Index: 528