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

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

Neuron 2200 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.6717. Min Act: -0.0001

Data Index: 993697 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.7486. Min Act: -0.0001

Data Index: 1245365 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.7455. Min Act: -0.0001

Data Index: 1161848 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.5686. Min Act: -0.0001

Data Index: 1164207 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.5636. Min Act: -0.0001

Data Index: 338744 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3927. Min Act: -0.0001

Data Index: 1056532 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3519. Min Act: -0.0001

Data Index: 543046 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4081. Min Act: -0.0001

Data Index: 1139234 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.5330. Min Act: -0.0001

Data Index: 59091 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3768. Min Act: -0.0001

Data Index: 69808 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3292. Min Act: -0.0001

Data Index: 468476 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3841. Min Act: -0.0001

Data Index: 1079338 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2805. Min Act: -0.0001

Data Index: 76136 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3516. Min Act: -0.0001

Data Index: 523324 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2618. Min Act: -0.0001

Data Index: 1169239 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3239. Min Act: -0.0001

Data Index: 1057319 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.1995. Min Act: -0.0001

Data Index: 49977 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2347. Min Act: -0.0001

Data Index: 426954 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2995. Min Act: -0.0001

Data Index: 1086852 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2627. Min Act: -0.0001

Data Index: 110404 (C4 (Web Text))

Max Activating Token Index: 10