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

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

Neuron 5284 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4722. Min Act: -0.0000

Data Index: 286446 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1179874 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4626. Min Act: -0.0000

Data Index: 972130 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1151426 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4186. Min Act: -0.0000

Data Index: 453692 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4168. Min Act: -0.0000

Data Index: 100675 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3860. Min Act: -0.0000

Data Index: 786085 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3938. Min Act: -0.0000

Data Index: 611980 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3708. Min Act: -0.0000

Data Index: 380727 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3723. Min Act: -0.0000

Data Index: 74168 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3504. Min Act: -0.0000

Data Index: 347822 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1250247 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3025. Min Act: -0.0000

Data Index: 630371 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3421. Min Act: -0.0000

Data Index: 224160 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1518949 (Python Code)

Max Activating Token Index: 794

Text #15

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3238. Min Act: -0.0000

Data Index: 55563 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3328. Min Act: -0.0000

Data Index: 573984 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3196. Min Act: -0.0000

Data Index: 64441 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3169. Min Act: -0.0000

Data Index: 749630 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3262. Min Act: -0.0000

Data Index: 25380 (C4 (Web Text))

Max Activating Token Index: 466