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

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

Neuron 727 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0169. Min Range: -5.0169

Max Act: 5.0169. Min Act: -0.0000

Data Index: 1187518 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.5843. Min Act: -0.0000

Data Index: 1128603 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.5038. Min Act: -0.0000

Data Index: 811026 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.2934. Min Act: -0.0000

Data Index: 714984 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.1111. Min Act: -0.0000

Data Index: 1233742 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.4768. Min Act: -0.0000

Data Index: 1083591 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.1860. Min Act: -0.0000

Data Index: 229060 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.4878. Min Act: -0.0000

Data Index: 851461 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.3058. Min Act: -0.0000

Data Index: 369726 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.0985. Min Act: -0.0000

Data Index: 1094036 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.3649. Min Act: -0.0000

Data Index: 1211616 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.1645. Min Act: -0.0000

Data Index: 503285 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.2444. Min Act: -0.0000

Data Index: 667071 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.2470. Min Act: -0.0000

Data Index: 83924 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.0259. Min Act: -0.0000

Data Index: 340655 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.0290. Min Act: -0.0000

Data Index: 223114 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.2360. Min Act: -0.0000

Data Index: 436715 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 5.0169. Min Range: -5.0169

Max Act: 4.1802. Min Act: -0.0000

Data Index: 497688 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 5.0169. Min Range: -5.0169

Max Act: 3.9469. Min Act: -0.0000

Data Index: 209305 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 5.0169. Min Range: -5.0169

Max Act: 3.7668. Min Act: -0.0000

Data Index: 602114 (C4 (Web Text))

Max Activating Token Index: 1019