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

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

Neuron 3870 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: 0.6377. Min Range: -0.6377

Max Act: 0.6377. Min Act: -0.0000

Data Index: 739451 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1091239 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.6004. Min Act: -0.0000

Data Index: 198306 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.5572. Min Act: -0.0000

Data Index: 356357 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.5334. Min Act: -0.0000

Data Index: 260384 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.5121. Min Act: -0.0000

Data Index: 711497 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4873. Min Act: -0.0000

Data Index: 865007 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4888. Min Act: -0.0000

Data Index: 163040 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.5088. Min Act: -0.0000

Data Index: 853264 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4919. Min Act: -0.0000

Data Index: 454117 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4695. Min Act: -0.0000

Data Index: 384141 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4615. Min Act: -0.0000

Data Index: 615328 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4920. Min Act: -0.0000

Data Index: 792669 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1244408 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4912. Min Act: -0.0000

Data Index: 540815 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1076235 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1353020 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4841. Min Act: -0.0000

Data Index: 133112 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4783. Min Act: -0.0000

Data Index: 13314 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.6377. Min Range: -0.6377

Max Act: 0.4628. Min Act: -0.0000

Data Index: 593887 (C4 (Web Text))

Max Activating Token Index: 902