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

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

Neuron 5892 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: 3.5212. Min Range: -3.5212

Max Act: 3.5212. Min Act: -0.0001

Data Index: 1031758 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 3.5212. Min Range: -3.5212

Max Act: 3.2257. Min Act: -0.0000

Data Index: 1304216 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 3.5212. Min Range: -3.5212

Max Act: 3.3498. Min Act: -0.0000

Data Index: 1081508 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 3.5212. Min Range: -3.5212

Max Act: 3.2772. Min Act: -0.0000

Data Index: 52489 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 3.5212. Min Range: -3.5212

Max Act: 3.3847. Min Act: -0.0000

Data Index: 84666 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 3.5212. Min Range: -3.5212

Max Act: 3.3297. Min Act: -0.0001

Data Index: 430362 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 3.5212. Min Range: -3.5212

Max Act: 3.2236. Min Act: -0.0000

Data Index: 98884 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 3.5212. Min Range: -3.5212

Max Act: 2.9427. Min Act: -0.0000

Data Index: 345447 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 3.5212. Min Range: -3.5212

Max Act: 3.0328. Min Act: -0.0001

Data Index: 1307431 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 3.5212. Min Range: -3.5212

Max Act: 3.0141. Min Act: -0.0001

Data Index: 1234550 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 3.5212. Min Range: -3.5212

Max Act: 2.8905. Min Act: -0.0000

Data Index: 1201781 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 3.5212. Min Range: -3.5212

Max Act: 3.1482. Min Act: -0.0001

Data Index: 546740 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 3.5212. Min Range: -3.5212

Max Act: 2.8594. Min Act: -0.0000

Data Index: 1042857 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 3.5212. Min Range: -3.5212

Max Act: 3.0634. Min Act: -0.0001

Data Index: 639069 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 3.5212. Min Range: -3.5212

Max Act: 2.8784. Min Act: -0.0001

Data Index: 617977 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 3.5212. Min Range: -3.5212

Max Act: 2.6491. Min Act: -0.0001

Data Index: 55854 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 3.5212. Min Range: -3.5212

Max Act: 2.7454. Min Act: -0.0000

Data Index: 204515 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 3.5212. Min Range: -3.5212

Max Act: 2.8711. Min Act: -0.0001

Data Index: 664916 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 3.5212. Min Range: -3.5212

Max Act: 2.7967. Min Act: -0.0000

Data Index: 521688 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.5212. Min Range: -3.5212

Max Act: 2.9309. Min Act: -0.0000

Data Index: 870766 (C4 (Web Text))

Max Activating Token Index: 584