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

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

Neuron 3276 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.8136. Min Act: -0.0002

Data Index: 153470 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.8916. Min Act: -0.0002

Data Index: 1290205 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6675. Min Act: -0.0002

Data Index: 396699 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6744. Min Act: -0.0002

Data Index: 1057849 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6116. Min Act: -0.0002

Data Index: 663693 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6553. Min Act: -0.0002

Data Index: 965410 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5700. Min Act: -0.0002

Data Index: 76598 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.7088. Min Act: -0.0002

Data Index: 632039 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6828. Min Act: -0.0001

Data Index: 71421 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6079. Min Act: -0.0002

Data Index: 1103991 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6266. Min Act: -0.0002

Data Index: 19570 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5629. Min Act: -0.0002

Data Index: 26789 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6164. Min Act: -0.0002

Data Index: 780804 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6198. Min Act: -0.0002

Data Index: 522525 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6225. Min Act: -0.0002

Data Index: 1269285 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6381. Min Act: -0.0001

Data Index: 182338 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5557. Min Act: -0.0002

Data Index: 569014 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6247. Min Act: -0.0001

Data Index: 643166 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.5745. Min Act: -0.0002

Data Index: 370869 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.8916. Min Range: -0.8916

Max Act: 0.6003. Min Act: -0.0002

Data Index: 322569 (C4 (Web Text))

Max Activating Token Index: 655