Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 493 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.5486. Min Act: -0.0002

Data Index: 177137 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4829. Min Act: -0.0002

Data Index: 1023594 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4589. Min Act: -0.0002

Data Index: 540440 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4449. Min Act: -0.0002

Data Index: 26606 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4696. Min Act: -0.0002

Data Index: 1108480 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4150. Min Act: -0.0002

Data Index: 1000770 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4400. Min Act: -0.0002

Data Index: 400453 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4267. Min Act: -0.0002

Data Index: 436956 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4350. Min Act: -0.0002

Data Index: 218251 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4293. Min Act: -0.0002

Data Index: 1162648 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4286. Min Act: -0.0002

Data Index: 213834 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4250. Min Act: -0.0002

Data Index: 1000447 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4136. Min Act: -0.0002

Data Index: 949154 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4327. Min Act: -0.0002

Data Index: 118574 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4128. Min Act: -0.0002

Data Index: 658444 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4123. Min Act: -0.0002

Data Index: 1352652 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3968. Min Act: -0.0002

Data Index: 974729 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3912. Min Act: -0.0002

Data Index: 133426 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.3924. Min Act: -0.0002

Data Index: 384247 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.5486. Min Range: -0.5486

Max Act: 0.4036. Min Act: -0.0002

Data Index: 671867 (C4 (Web Text))

Max Activating Token Index: 89