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

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

Neuron 3944 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.3107. Min Act: -0.0000

Data Index: 81229 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2861. Min Act: -0.0001

Data Index: 1430238 (Python Code)

Max Activating Token Index: 615

Text #2

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2734. Min Act: -0.0000

Data Index: 564405 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2735. Min Act: -0.0000

Data Index: 779956 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2657. Min Act: -0.0000

Data Index: 718033 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2702. Min Act: -0.0000

Data Index: 187130 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2587. Min Act: -0.0001

Data Index: 1268860 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1630859 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1360480 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2430. Min Act: -0.0001

Data Index: 539901 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2604. Min Act: -0.0000

Data Index: 163366 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2387. Min Act: -0.0001

Data Index: 32247 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2308. Min Act: -0.0001

Data Index: 1605811 (Python Code)

Max Activating Token Index: 171

Text #13

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2470. Min Act: -0.0001

Data Index: 782449 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2361. Min Act: -0.0000

Data Index: 226439 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1044224 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2426. Min Act: -0.0001

Data Index: 1522700 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1078960 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2212. Min Act: -0.0000

Data Index: 394966 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1328098 (C4 (Web Text))

Max Activating Token Index: 136