Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2231 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.7134. Min Act: -0.0000

Data Index: 931519 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.5368. Min Act: -0.0000

Data Index: 443525 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.6515. Min Act: -0.0000

Data Index: 926740 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.6427. Min Act: -0.0000

Data Index: 1300705 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.6213. Min Act: -0.0000

Data Index: 160908 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.3100. Min Act: -0.0000

Data Index: 674891 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.2940. Min Act: -0.0000

Data Index: 706322 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.3926. Min Act: -0.0000

Data Index: 1070139 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.2196. Min Act: -0.0000

Data Index: 1066460 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.5191. Min Act: -0.0000

Data Index: 127233 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.1537. Min Act: -0.0000

Data Index: 897619 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.1111. Min Act: -0.0000

Data Index: 1055216 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.1211. Min Act: -0.0000

Data Index: 1061468 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.2483. Min Act: -0.0000

Data Index: 301458 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.0673. Min Act: -0.0000

Data Index: 73917 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.1862. Min Act: -0.0000

Data Index: 1272642 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 3.7134. Min Range: -3.7134

Max Act: 3.1501. Min Act: -0.0000

Data Index: 21729 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 3.7134. Min Range: -3.7134

Max Act: 2.9759. Min Act: -0.0000

Data Index: 1336992 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 3.7134. Min Range: -3.7134

Max Act: 2.9417. Min Act: 0.0000

Data Index: 315329 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 3.7134. Min Range: -3.7134

Max Act: 2.9886. Min Act: -0.0000

Data Index: 717047 (C4 (Web Text))

Max Activating Token Index: 186