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

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

Neuron 3130 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5024. Min Range: -1.5024

Max Act: 1.5024. Min Act: -0.0000

Data Index: 213807 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 1.5024. Min Range: -1.5024

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1530367 (Python Code)

Max Activating Token Index: 337

Text #2

Max Range: 1.5024. Min Range: -1.5024

Max Act: 1.1008. Min Act: -0.0000

Data Index: 896587 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1055822 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.9662. Min Act: -0.0000

Data Index: 759213 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1454853 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.8044. Min Act: -0.0000

Data Index: 231492 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.7637. Min Act: -0.0000

Data Index: 954488 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.7331. Min Act: -0.0000

Data Index: 982146 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.8031. Min Act: -0.0000

Data Index: 384384 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.7392. Min Act: -0.0000

Data Index: 807558 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1333131 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1270112 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.7454. Min Act: -0.0000

Data Index: 562343 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1176479 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.7143. Min Act: -0.0000

Data Index: 543670 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.6962. Min Act: -0.0000

Data Index: 640759 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.6872. Min Act: -0.0000

Data Index: 69685 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.7012. Min Act: -0.0000

Data Index: 950458 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 1.5024. Min Range: -1.5024

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1606819 (Python Code)

Max Activating Token Index: 988