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

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

Neuron 4035 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.3095. Min Act: -0.0001

Data Index: 948802 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.3219. Min Act: -0.0001

Data Index: 930447 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2886. Min Act: -0.0001

Data Index: 86314 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2707. Min Act: -0.0000

Data Index: 886343 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2695. Min Act: -0.0000

Data Index: 84305 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2610. Min Act: -0.0000

Data Index: 470538 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2482. Min Act: -0.0001

Data Index: 522912 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2565. Min Act: -0.0001

Data Index: 657440 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2636. Min Act: -0.0001

Data Index: 895395 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2526. Min Act: -0.0001

Data Index: 772556 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2259. Min Act: -0.0001

Data Index: 546876 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2438. Min Act: -0.0001

Data Index: 123542 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1274433 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2360. Min Act: -0.0000

Data Index: 184430 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2282. Min Act: -0.0001

Data Index: 132858 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2368. Min Act: -0.0001

Data Index: 817034 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2192. Min Act: -0.0001

Data Index: 170640 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2101. Min Act: -0.0001

Data Index: 60268 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1064715 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.3219. Min Range: -0.3219

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1094092 (C4 (Web Text))

Max Activating Token Index: 492