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

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

Neuron 190 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: 0.8523. Min Range: -0.8523

Max Act: 0.8523. Min Act: -0.0000

Data Index: 803267 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.8499. Min Act: -0.0000

Data Index: 878113 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7594. Min Act: -0.0000

Data Index: 27568 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.7178. Min Act: -0.0000

Data Index: 889390 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6679. Min Act: -0.0000

Data Index: 267202 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1021808 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1247992 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1003559 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6267. Min Act: -0.0001

Data Index: 979835 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5692. Min Act: -0.0000

Data Index: 825264 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.6057. Min Act: -0.0000

Data Index: 554488 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5792. Min Act: -0.0000

Data Index: 392172 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5707. Min Act: -0.0000

Data Index: 846385 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1108700 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1305850 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5965. Min Act: -0.0000

Data Index: 522324 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1007399 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5711. Min Act: -0.0001

Data Index: 263465 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5366. Min Act: -0.0000

Data Index: 548795 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.8523. Min Range: -0.8523

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1229379 (C4 (Web Text))

Max Activating Token Index: 245