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

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

Neuron 91 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: 0.8016. Min Range: -0.8016

Max Act: 0.8016. Min Act: -0.0000

Data Index: 142588 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6870. Min Act: -0.0001

Data Index: 817195 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6566. Min Act: -0.0001

Data Index: 715433 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6016. Min Act: -0.0000

Data Index: 609868 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6135. Min Act: -0.0000

Data Index: 725209 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5860. Min Act: -0.0001

Data Index: 1242731 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5676. Min Act: -0.0000

Data Index: 108337 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5692. Min Act: -0.0000

Data Index: 26217 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5496. Min Act: -0.0000

Data Index: 741331 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5661. Min Act: -0.0000

Data Index: 956217 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5585. Min Act: -0.0000

Data Index: 988846 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5267. Min Act: -0.0001

Data Index: 424908 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1228084 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5082. Min Act: -0.0000

Data Index: 136606 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5411. Min Act: -0.0000

Data Index: 277244 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5415. Min Act: -0.0000

Data Index: 480558 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5398. Min Act: -0.0001

Data Index: 1177970 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5223. Min Act: -0.0001

Data Index: 993602 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1275120 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5300. Min Act: -0.0001

Data Index: 394185 (C4 (Web Text))

Max Activating Token Index: 1012