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

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

Neuron 5012 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4446. Min Range: -2.4446

Max Act: 2.4446. Min Act: -0.0001

Data Index: 58550 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 2.4446. Min Range: -2.4446

Max Act: 2.4349. Min Act: -0.0001

Data Index: 200597 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 2.4446. Min Range: -2.4446

Max Act: 2.1689. Min Act: -0.0000

Data Index: 97225 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 2.4446. Min Range: -2.4446

Max Act: 2.1903. Min Act: -0.0001

Data Index: 1110353 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 2.4446. Min Range: -2.4446

Max Act: 2.0569. Min Act: -0.0000

Data Index: 710582 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 2.4446. Min Range: -2.4446

Max Act: 2.0364. Min Act: -0.0000

Data Index: 501299 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.9536. Min Act: -0.0001

Data Index: 989786 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.9737. Min Act: -0.0000

Data Index: 795128 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.8877. Min Act: -0.0000

Data Index: 535828 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.9745. Min Act: -0.0000

Data Index: 1090328 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.8724. Min Act: -0.0001

Data Index: 189384 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.8630. Min Act: -0.0000

Data Index: 1095047 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.8553. Min Act: -0.0000

Data Index: 725924 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.8052. Min Act: -0.0001

Data Index: 706285 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.7217. Min Act: -0.0001

Data Index: 1271645 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.6124. Min Act: -0.0001

Data Index: 702399 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.6690. Min Act: -0.0000

Data Index: 396002 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.7626. Min Act: -0.0000

Data Index: 500728 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.6718. Min Act: -0.0001

Data Index: 101577 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 2.4446. Min Range: -2.4446

Max Act: 1.7664. Min Act: -0.0000

Data Index: 1215517 (C4 (Web Text))

Max Activating Token Index: 777