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

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

Neuron 2104 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5329. Min Range: -1.5329

Max Act: 1.5329. Min Act: -0.0001

Data Index: 1550168 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 1.5329. Min Range: -1.5329

Max Act: 1.3951. Min Act: -0.0001

Data Index: 576319 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 1.5329. Min Range: -1.5329

Max Act: 1.4068. Min Act: -0.0001

Data Index: 1315784 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 1.5329. Min Range: -1.5329

Max Act: 1.2562. Min Act: -0.0001

Data Index: 1505024 (Python Code)

Max Activating Token Index: 291

Text #4

Max Range: 1.5329. Min Range: -1.5329

Max Act: 1.1421. Min Act: -0.0001

Data Index: 1261127 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.9836. Min Act: -0.0001

Data Index: 928217 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 1.5329. Min Range: -1.5329

Max Act: 1.0567. Min Act: -0.0001

Data Index: 1383230 (Python Code)

Max Activating Token Index: 507

Text #7

Max Range: 1.5329. Min Range: -1.5329

Max Act: 1.0149. Min Act: -0.0001

Data Index: 1503492 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 1.5329. Min Range: -1.5329

Max Act: 1.0779. Min Act: -0.0001

Data Index: 1564020 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.9683. Min Act: -0.0001

Data Index: 1385239 (Python Code)

Max Activating Token Index: 910

Text #10

Max Range: 1.5329. Min Range: -1.5329

Max Act: 1.0681. Min Act: -0.0001

Data Index: 1582541 (Python Code)

Max Activating Token Index: 76

Text #11

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1323501 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.9206. Min Act: -0.0001

Data Index: 1296323 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.9231. Min Act: -0.0001

Data Index: 1519875 (Python Code)

Max Activating Token Index: 327

Text #14

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.9077. Min Act: -0.0001

Data Index: 1632233 (Python Code)

Max Activating Token Index: 450

Text #15

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.8687. Min Act: -0.0001

Data Index: 1391817 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.9053. Min Act: -0.0001

Data Index: 1406041 (Python Code)

Max Activating Token Index: 863

Text #17

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.9094. Min Act: -0.0001

Data Index: 1499819 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.8570. Min Act: -0.0001

Data Index: 1413289 (Python Code)

Max Activating Token Index: 921

Text #19

Max Range: 1.5329. Min Range: -1.5329

Max Act: 0.8791. Min Act: -0.0000

Data Index: 529649 (C4 (Web Text))

Max Activating Token Index: 365