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

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

Neuron 3681 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.6127. Min Act: -0.0000

Data Index: 734583 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.4832. Min Act: -0.0000

Data Index: 526698 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.5718. Min Act: -0.0000

Data Index: 1127056 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.4177. Min Act: -0.0000

Data Index: 88163 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.4160. Min Act: -0.0000

Data Index: 111325 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.4937. Min Act: -0.0000

Data Index: 1282976 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.4828. Min Act: -0.0000

Data Index: 827884 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.5243. Min Act: -0.0000

Data Index: 1052279 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.3375. Min Act: -0.0000

Data Index: 78899 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.3488. Min Act: -0.0000

Data Index: 699055 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.4437. Min Act: -0.0000

Data Index: 693062 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.2132. Min Act: -0.0000

Data Index: 556021 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.2031. Min Act: -0.0000

Data Index: 127799 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.2768. Min Act: -0.0000

Data Index: 1161501 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.2883. Min Act: -0.0000

Data Index: 159080 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.2787. Min Act: -0.0000

Data Index: 1001684 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.2652. Min Act: -0.0000

Data Index: 1180072 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.2221. Min Act: -0.0000

Data Index: 1033373 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.0905. Min Act: -0.0000

Data Index: 337879 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 2.6127. Min Range: -2.6127

Max Act: 2.2056. Min Act: -0.0000

Data Index: 928543 (C4 (Web Text))

Max Activating Token Index: 963