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

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

Neuron 3804 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3389. Min Act: -0.0000

Data Index: 677686 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3453. Min Act: -0.0000

Data Index: 670678 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3442. Min Act: 0.0000

Data Index: 876411 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3274. Min Act: -0.0000

Data Index: 129864 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3188. Min Act: -0.0000

Data Index: 247858 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3054. Min Act: 0.0001

Data Index: 587298 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3152. Min Act: 0.0000

Data Index: 513015 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3080. Min Act: -0.0000

Data Index: 184352 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1099647 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3039. Min Act: -0.0000

Data Index: 972770 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2984. Min Act: -0.0001

Data Index: 585927 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2952. Min Act: -0.0000

Data Index: 533971 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3030. Min Act: -0.0000

Data Index: 484882 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2951. Min Act: -0.0000

Data Index: 535466 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2925. Min Act: -0.0001

Data Index: 608370 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2921. Min Act: 0.0000

Data Index: 767384 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2823. Min Act: -0.0000

Data Index: 347399 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3003. Min Act: -0.0000

Data Index: 136597 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2900. Min Act: 0.0000

Data Index: 425030 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2880. Min Act: -0.0000

Data Index: 955788 (C4 (Web Text))

Max Activating Token Index: 422