Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4076 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.2315. Min Act: -0.0001

Data Index: 864076 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.1025. Min Act: -0.0001

Data Index: 991795 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 1.2315. Min Range: -1.2315

Max Act: 1.1088. Min Act: -0.0001

Data Index: 1147129 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9378. Min Act: -0.0001

Data Index: 531374 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9488. Min Act: -0.0001

Data Index: 43234 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9276. Min Act: -0.0001

Data Index: 172619 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8711. Min Act: -0.0001

Data Index: 126927 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9808. Min Act: -0.0001

Data Index: 818873 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8758. Min Act: -0.0001

Data Index: 22701 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8249. Min Act: -0.0001

Data Index: 222140 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8459. Min Act: -0.0001

Data Index: 107812 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8141. Min Act: -0.0001

Data Index: 963027 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.9229. Min Act: -0.0001

Data Index: 1159571 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8795. Min Act: -0.0001

Data Index: 508387 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8516. Min Act: -0.0001

Data Index: 156899 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8560. Min Act: -0.0001

Data Index: 1063443 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8251. Min Act: -0.0001

Data Index: 147861 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8756. Min Act: -0.0001

Data Index: 266230 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8201. Min Act: -0.0001

Data Index: 833635 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 1.2315. Min Range: -1.2315

Max Act: 0.8490. Min Act: -0.0001

Data Index: 320038 (C4 (Web Text))

Max Activating Token Index: 3