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

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

Neuron 3862 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: 0.5169. Min Range: -0.5169

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1166880 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5169. Min Act: -0.0001

Data Index: 1106652 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4638. Min Act: -0.0000

Data Index: 825707 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4081. Min Act: -0.0000

Data Index: 857679 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4572. Min Act: -0.0001

Data Index: 665725 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4336. Min Act: -0.0000

Data Index: 993424 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4145. Min Act: -0.0000

Data Index: 503660 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3757. Min Act: -0.0001

Data Index: 1300967 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3499. Min Act: -0.0001

Data Index: 1616726 (Python Code)

Max Activating Token Index: 668

Text #9

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3999. Min Act: -0.0001

Data Index: 618344 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3975. Min Act: -0.0000

Data Index: 62486 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3548. Min Act: -0.0000

Data Index: 883761 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3901. Min Act: -0.0000

Data Index: 890998 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3289. Min Act: -0.0000

Data Index: 958398 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3630. Min Act: -0.0000

Data Index: 110414 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3148. Min Act: -0.0000

Data Index: 241594 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3969. Min Act: -0.0000

Data Index: 809312 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3741. Min Act: -0.0000

Data Index: 679360 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1392946 (Python Code)

Max Activating Token Index: 445

Text #19

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3413. Min Act: -0.0001

Data Index: 161443 (C4 (Web Text))

Max Activating Token Index: 949