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

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

Neuron 4520 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0544. Min Range: -2.0544

Max Act: 2.0544. Min Act: -0.0000

Data Index: 1287492 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.7403. Min Act: -0.0001

Data Index: 1188971 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.5210. Min Act: -0.0000

Data Index: 477543 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4938. Min Act: -0.0000

Data Index: 990539 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4686. Min Act: -0.0001

Data Index: 411502 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.6207. Min Act: -0.0001

Data Index: 656902 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.3613. Min Act: -0.0000

Data Index: 990296 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4732. Min Act: -0.0001

Data Index: 862321 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4119. Min Act: -0.0001

Data Index: 979656 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4527. Min Act: -0.0000

Data Index: 438308 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.3577. Min Act: -0.0000

Data Index: 1131270 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.3586. Min Act: -0.0000

Data Index: 1124980 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.3924. Min Act: -0.0000

Data Index: 86414 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1352592 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.3038. Min Act: -0.0001

Data Index: 946375 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1258455 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4065. Min Act: -0.0000

Data Index: 310674 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.3250. Min Act: -0.0001

Data Index: 558717 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.3407. Min Act: -0.0000

Data Index: 151049 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.2259. Min Act: -0.0000

Data Index: 861656 (C4 (Web Text))

Max Activating Token Index: 532