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

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

Neuron 4501 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.1844. Min Range: -9.1844

Max Act: 9.1844. Min Act: -0.0000

Data Index: 366088 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 9.1844. Min Range: -9.1844

Max Act: 7.2317. Min Act: -0.0000

Data Index: 362487 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.9239. Min Act: -0.0000

Data Index: 475466 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.8466. Min Act: -0.0000

Data Index: 417647 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 9.1844. Min Range: -9.1844

Max Act: 7.0085. Min Act: -0.0000

Data Index: 771382 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.6540. Min Act: -0.0000

Data Index: 1131910 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.6025. Min Act: -0.0000

Data Index: 1280699 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.3607. Min Act: -0.0000

Data Index: 218576 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 9.1844. Min Range: -9.1844

Max Act: 5.9367. Min Act: -0.0000

Data Index: 1079279 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.1117. Min Act: -0.0000

Data Index: 270818 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 9.1844. Min Range: -9.1844

Max Act: 5.9722. Min Act: -0.0000

Data Index: 883528 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 9.1844. Min Range: -9.1844

Max Act: 5.8027. Min Act: -0.0000

Data Index: 136279 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.0194. Min Act: -0.0000

Data Index: 1068180 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.0652. Min Act: -0.0000

Data Index: 1322595 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.0364. Min Act: -0.0000

Data Index: 546598 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.2406. Min Act: -0.0000

Data Index: 332 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.0192. Min Act: -0.0000

Data Index: 567781 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.2140. Min Act: -0.0000

Data Index: 112153 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 9.1844. Min Range: -9.1844

Max Act: 5.8411. Min Act: -0.0000

Data Index: 542383 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 9.1844. Min Range: -9.1844

Max Act: 6.3720. Min Act: -0.0000

Data Index: 150310 (C4 (Web Text))

Max Activating Token Index: 152