Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2352 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.3544. Min Act: -0.0000

Data Index: 656994 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.1264. Min Act: -0.0000

Data Index: 181814 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.9891. Min Act: -0.0000

Data Index: 150297 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.7852. Min Act: -0.0000

Data Index: 993164 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.7688. Min Act: -0.0000

Data Index: 264811 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.8384. Min Act: -0.0000

Data Index: 738470 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.7322. Min Act: -0.0000

Data Index: 745496 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.5900. Min Act: -0.0000

Data Index: 965539 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.6764. Min Act: -0.0000

Data Index: 1123922 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.6672. Min Act: -0.0000

Data Index: 189953 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.6460. Min Act: -0.0000

Data Index: 558779 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1090912 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.4650. Min Act: -0.0000

Data Index: 562844 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.6347. Min Act: -0.0000

Data Index: 729130 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.5982. Min Act: -0.0000

Data Index: 465516 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.5740. Min Act: -0.0000

Data Index: 574657 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.6392. Min Act: -0.0000

Data Index: 773547 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.5404. Min Act: -0.0000

Data Index: 250236 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.5123. Min Act: -0.0000

Data Index: 739324 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.5041. Min Act: -0.0000

Data Index: 457318 (C4 (Web Text))

Max Activating Token Index: 658