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

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

Neuron 5494 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: 1.9818. Min Range: -1.9818

Max Act: 1.9818. Min Act: -0.0002

Data Index: 944461 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.8675. Min Act: -0.0002

Data Index: 162267 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.8743. Min Act: -0.0002

Data Index: 703636 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.7372. Min Act: -0.0002

Data Index: 641923 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.7820. Min Act: -0.0002

Data Index: 10389 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.6421. Min Act: -0.0002

Data Index: 757069 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.6523. Min Act: -0.0002

Data Index: 293413 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.6357. Min Act: -0.0002

Data Index: 656300 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.7180. Min Act: -0.0002

Data Index: 440634 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.6222. Min Act: -0.0002

Data Index: 401794 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.5473. Min Act: -0.0002

Data Index: 369693 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.5668. Min Act: -0.0002

Data Index: 1050880 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.5820. Min Act: -0.0002

Data Index: 1145388 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.4362. Min Act: -0.0002

Data Index: 1309153 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.5166. Min Act: -0.0002

Data Index: 501607 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.4281. Min Act: -0.0002

Data Index: 780009 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.5142. Min Act: -0.0002

Data Index: 1341432 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.4837. Min Act: -0.0002

Data Index: 922925 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.4766. Min Act: -0.0002

Data Index: 987954 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 1.9818. Min Range: -1.9818

Max Act: 1.4882. Min Act: -0.0002

Data Index: 951630 (C4 (Web Text))

Max Activating Token Index: 604