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

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

Neuron 26 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: 3.9299. Min Range: -3.9299

Max Act: 3.9299. Min Act: -0.0000

Data Index: 1564208 (Python Code)

Max Activating Token Index: 982

Text #1

Max Range: 3.9299. Min Range: -3.9299

Max Act: 3.4118. Min Act: -0.0000

Data Index: 281549 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 3.9299. Min Range: -3.9299

Max Act: 3.2078. Min Act: -0.0000

Data Index: 336389 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 3.9299. Min Range: -3.9299

Max Act: 3.4477. Min Act: -0.0000

Data Index: 1215152 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.9385. Min Act: -0.0000

Data Index: 673771 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.8618. Min Act: -0.0000

Data Index: 844927 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.9320. Min Act: -0.0000

Data Index: 549733 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.8498. Min Act: -0.0000

Data Index: 340078 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.8211. Min Act: -0.0000

Data Index: 1380333 (Python Code)

Max Activating Token Index: 495

Text #9

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.7891. Min Act: -0.0000

Data Index: 382994 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.6590. Min Act: -0.0000

Data Index: 1062705 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.7561. Min Act: -0.0000

Data Index: 1324072 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.8774. Min Act: -0.0000

Data Index: 1067480 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.7364. Min Act: -0.0000

Data Index: 774509 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.6889. Min Act: -0.0000

Data Index: 1324918 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.8065. Min Act: -0.0000

Data Index: 895921 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.8286. Min Act: -0.0000

Data Index: 721321 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.5192. Min Act: -0.0000

Data Index: 1534530 (Python Code)

Max Activating Token Index: 620

Text #18

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.5219. Min Act: -0.0000

Data Index: 1268362 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 3.9299. Min Range: -3.9299

Max Act: 2.6533. Min Act: -0.0000

Data Index: 621761 (C4 (Web Text))

Max Activating Token Index: 178