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

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

Neuron 989 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.4109. Min Act: -0.0000

Data Index: 1135240 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.1481. Min Act: 0.0001

Data Index: 1032615 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.1936. Min Act: -0.0000

Data Index: 678443 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.0858. Min Act: 0.0000

Data Index: 678760 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 1.4109. Min Range: -1.4109

Max Act: 1.0683. Min Act: 0.0000

Data Index: 143212 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1207970 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.9329. Min Act: -0.0000

Data Index: 884775 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.9284. Min Act: -0.0000

Data Index: 925444 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8686. Min Act: -0.0000

Data Index: 133187 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1222588 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8439. Min Act: 0.0000

Data Index: 507998 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8274. Min Act: -0.0000

Data Index: 958971 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8176. Min Act: -0.0000

Data Index: 150659 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.7854. Min Act: 0.0001

Data Index: 581085 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1234420 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8192. Min Act: -0.0000

Data Index: 850050 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.7876. Min Act: -0.0000

Data Index: 594677 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.7568. Min Act: -0.0000

Data Index: 452281 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.8219. Min Act: 0.0000

Data Index: 280621 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 1.4109. Min Range: -1.4109

Max Act: 0.7830. Min Act: 0.0000

Data Index: 1010853 (C4 (Web Text))

Max Activating Token Index: 640