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

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

Neuron 2704 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1359014 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.9418. Min Act: 0.0000

Data Index: 471318 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1127052 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8874. Min Act: -0.0000

Data Index: 991434 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1059214 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8965. Min Act: -0.0000

Data Index: 867568 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.9196. Min Act: -0.0000

Data Index: 616637 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8938. Min Act: -0.0000

Data Index: 640812 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8787. Min Act: -0.0000

Data Index: 719945 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8411. Min Act: -0.0000

Data Index: 285828 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8674. Min Act: -0.0000

Data Index: 1144820 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1138905 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8486. Min Act: -0.0000

Data Index: 182133 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8403. Min Act: -0.0000

Data Index: 505526 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1013415 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1217747 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8565. Min Act: -0.0000

Data Index: 338231 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8167. Min Act: -0.0000

Data Index: 37363 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8320. Min Act: 0.0000

Data Index: 1200266 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8114. Min Act: -0.0000

Data Index: 936665 (C4 (Web Text))

Max Activating Token Index: 202