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

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

Neuron 3063 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.7251. Min Act: -0.0000

Data Index: 683262 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.7256. Min Act: -0.0001

Data Index: 165800 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.7218. Min Act: -0.0001

Data Index: 628653 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6310. Min Act: -0.0000

Data Index: 94891 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6231. Min Act: -0.0001

Data Index: 334966 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6046. Min Act: -0.0000

Data Index: 348669 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5848. Min Act: -0.0000

Data Index: 879592 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6411. Min Act: -0.0001

Data Index: 145644 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5634. Min Act: -0.0001

Data Index: 773994 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5839. Min Act: -0.0001

Data Index: 566090 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5796. Min Act: -0.0001

Data Index: 945096 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5611. Min Act: -0.0001

Data Index: 93793 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.6064. Min Act: -0.0000

Data Index: 27932 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5267. Min Act: -0.0001

Data Index: 926894 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5753. Min Act: -0.0000

Data Index: 116090 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5469. Min Act: -0.0001

Data Index: 255027 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5576. Min Act: -0.0000

Data Index: 851346 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5155. Min Act: -0.0000

Data Index: 573834 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5196. Min Act: -0.0001

Data Index: 82485 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.7256. Min Range: -0.7256

Max Act: 0.5159. Min Act: -0.0001

Data Index: 1141308 (C4 (Web Text))

Max Activating Token Index: 63