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

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

Neuron 3888 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7757. Min Act: -0.0001

Data Index: 875587 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7030. Min Act: -0.0001

Data Index: 659162 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7063. Min Act: -0.0001

Data Index: 1153473 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7590. Min Act: -0.0001

Data Index: 1196799 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7326. Min Act: -0.0001

Data Index: 236310 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6115. Min Act: -0.0001

Data Index: 820479 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7267. Min Act: -0.0001

Data Index: 43437 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6746. Min Act: -0.0001

Data Index: 447396 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5736. Min Act: -0.0001

Data Index: 447083 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5906. Min Act: -0.0001

Data Index: 515209 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6468. Min Act: -0.0001

Data Index: 769534 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6894. Min Act: -0.0001

Data Index: 571411 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6192. Min Act: -0.0001

Data Index: 708869 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6253. Min Act: -0.0001

Data Index: 1239466 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6693. Min Act: -0.0001

Data Index: 169663 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6471. Min Act: -0.0001

Data Index: 786323 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6527. Min Act: -0.0001

Data Index: 191286 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5953. Min Act: -0.0001

Data Index: 1058762 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6681. Min Act: -0.0001

Data Index: 635007 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6136. Min Act: -0.0001

Data Index: 651085 (C4 (Web Text))

Max Activating Token Index: 702