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

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

Neuron 2041 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: 2.7579. Min Range: -2.7579

Max Act: 2.7579. Min Act: -0.0000

Data Index: 511263 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 2.7579. Min Range: -2.7579

Max Act: 2.3624. Min Act: -0.0000

Data Index: 438345 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 2.7579. Min Range: -2.7579

Max Act: 2.3818. Min Act: -0.0000

Data Index: 1323552 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 2.7579. Min Range: -2.7579

Max Act: 2.1563. Min Act: -0.0000

Data Index: 837176 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.9826. Min Act: -0.0000

Data Index: 315841 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 2.7579. Min Range: -2.7579

Max Act: 2.0249. Min Act: -0.0000

Data Index: 965833 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.9650. Min Act: 0.0000

Data Index: 884075 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 2.7579. Min Range: -2.7579

Max Act: 2.0601. Min Act: -0.0000

Data Index: 1290528 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.9201. Min Act: -0.0000

Data Index: 861504 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.9290. Min Act: -0.0000

Data Index: 472316 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.9043. Min Act: -0.0000

Data Index: 988288 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.9223. Min Act: -0.0000

Data Index: 1080363 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 2.7579. Min Range: -2.7579

Max Act: 2.0259. Min Act: -0.0000

Data Index: 959927 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.9965. Min Act: -0.0000

Data Index: 1156803 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.8611. Min Act: -0.0000

Data Index: 372305 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.8593. Min Act: -0.0000

Data Index: 1054391 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.7348. Min Act: -0.0000

Data Index: 1067306 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.8088. Min Act: -0.0000

Data Index: 591923 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.6255. Min Act: -0.0000

Data Index: 725878 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 2.7579. Min Range: -2.7579

Max Act: 1.7975. Min Act: -0.0000

Data Index: 109643 (C4 (Web Text))

Max Activating Token Index: 655