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

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

Neuron 3365 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: 0.3898. Min Range: -0.3898

Max Act: 0.3898. Min Act: -0.0001

Data Index: 379067 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3886. Min Act: -0.0000

Data Index: 823175 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3790. Min Act: -0.0001

Data Index: 1303323 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3534. Min Act: -0.0000

Data Index: 452301 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3627. Min Act: -0.0001

Data Index: 1076705 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3507. Min Act: -0.0000

Data Index: 959085 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3471. Min Act: -0.0001

Data Index: 1173167 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3472. Min Act: -0.0001

Data Index: 580043 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1278899 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3083. Min Act: 0.0001

Data Index: 758283 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3279. Min Act: -0.0000

Data Index: 451075 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3302. Min Act: -0.0000

Data Index: 896000 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3252. Min Act: -0.0000

Data Index: 398707 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3105. Min Act: -0.0001

Data Index: 219375 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.2977. Min Act: -0.0000

Data Index: 177369 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3270. Min Act: -0.0000

Data Index: 648527 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3133. Min Act: -0.0001

Data Index: 878890 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1326479 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3042. Min Act: -0.0001

Data Index: 923567 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.3898. Min Range: -0.3898

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1308295 (C4 (Web Text))

Max Activating Token Index: 579