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

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

Neuron 3184 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.2431. Min Act: -0.0000

Data Index: 912867 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.1447. Min Act: -0.0000

Data Index: 691811 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.0567. Min Act: -0.0000

Data Index: 830334 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.0391. Min Act: -0.0000

Data Index: 826298 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9943. Min Act: -0.0001

Data Index: 289571 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8602. Min Act: -0.0001

Data Index: 645145 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9162. Min Act: -0.0001

Data Index: 764716 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.0178. Min Act: -0.0000

Data Index: 602513 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8598. Min Act: -0.0001

Data Index: 962579 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8259. Min Act: -0.0001

Data Index: 340644 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8704. Min Act: -0.0001

Data Index: 1123650 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8383. Min Act: -0.0001

Data Index: 346819 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8589. Min Act: -0.0000

Data Index: 65410 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8287. Min Act: -0.0001

Data Index: 1279924 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8558. Min Act: -0.0000

Data Index: 175096 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8928. Min Act: -0.0001

Data Index: 671716 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8375. Min Act: -0.0001

Data Index: 1072216 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8159. Min Act: -0.0001

Data Index: 600718 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7921. Min Act: -0.0000

Data Index: 489726 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7004. Min Act: -0.0001

Data Index: 202983 (C4 (Web Text))

Max Activating Token Index: 914