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

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

Neuron 1472 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: 3.1988. Min Range: -3.1988

Max Act: 3.1988. Min Act: -0.0000

Data Index: 959061 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 3.1988. Min Range: -3.1988

Max Act: 3.0497. Min Act: -0.0000

Data Index: 629696 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.8358. Min Act: -0.0000

Data Index: 1126382 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.5794. Min Act: -0.0000

Data Index: 513770 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.7178. Min Act: -0.0000

Data Index: 752770 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.4668. Min Act: -0.0000

Data Index: 661412 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.2997. Min Act: -0.0000

Data Index: 846497 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.2116. Min Act: -0.0000

Data Index: 784226 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.0728. Min Act: -0.0000

Data Index: 640886 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.0528. Min Act: -0.0000

Data Index: 228741 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 3.1988. Min Range: -3.1988

Max Act: 1.8535. Min Act: -0.0000

Data Index: 1028014 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.1452. Min Act: -0.0000

Data Index: 625149 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 3.1988. Min Range: -3.1988

Max Act: 1.9045. Min Act: -0.0000

Data Index: 811042 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.0252. Min Act: -0.0000

Data Index: 1028082 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 3.1988. Min Range: -3.1988

Max Act: 1.8817. Min Act: -0.0000

Data Index: 634824 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.0735. Min Act: -0.0000

Data Index: 1056433 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 3.1988. Min Range: -3.1988

Max Act: 1.8395. Min Act: -0.0000

Data Index: 330068 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.0323. Min Act: -0.0000

Data Index: 172353 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 3.1988. Min Range: -3.1988

Max Act: 2.2574. Min Act: -0.0000

Data Index: 176076 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 3.1988. Min Range: -3.1988

Max Act: 1.9248. Min Act: -0.0000

Data Index: 840749 (C4 (Web Text))

Max Activating Token Index: 120