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

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

Neuron 2677 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.7120. Min Act: -0.0000

Data Index: 876590 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6044. Min Act: -0.0000

Data Index: 597976 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1269275 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6204. Min Act: -0.0000

Data Index: 422538 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6260. Min Act: -0.0000

Data Index: 735499 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5876. Min Act: -0.0000

Data Index: 201385 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6008. Min Act: -0.0000

Data Index: 82193 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5749. Min Act: -0.0000

Data Index: 316547 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5757. Min Act: -0.0000

Data Index: 169888 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1152209 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5661. Min Act: -0.0000

Data Index: 399164 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5502. Min Act: -0.0000

Data Index: 117904 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5109. Min Act: -0.0000

Data Index: 586438 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5669. Min Act: -0.0000

Data Index: 351506 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5352. Min Act: -0.0000

Data Index: 346425 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1144214 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.4854. Min Act: -0.0000

Data Index: 150645 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5352. Min Act: -0.0000

Data Index: 427293 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5227. Min Act: -0.0000

Data Index: 72879 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5210. Min Act: -0.0000

Data Index: 594066 (C4 (Web Text))

Max Activating Token Index: 584