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

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

Neuron 712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3398. Min Range: -3.3398

Max Act: 3.0465. Min Act: -0.0000

Data Index: 823093 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 3.3398. Min Range: -3.3398

Max Act: 3.3398. Min Act: -0.0000

Data Index: 77801 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.9797. Min Act: -0.0000

Data Index: 216523 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.9240. Min Act: -0.0000

Data Index: 268999 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 3.3398. Min Range: -3.3398

Max Act: 3.0249. Min Act: -0.0000

Data Index: 813256 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.8601. Min Act: -0.0000

Data Index: 826441 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.9419. Min Act: -0.0000

Data Index: 346188 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.9307. Min Act: -0.0000

Data Index: 610380 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.9474. Min Act: -0.0000

Data Index: 309306 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 3.3398. Min Range: -3.3398

Max Act: 3.0303. Min Act: -0.0000

Data Index: 517377 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.8251. Min Act: -0.0000

Data Index: 839293 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.9690. Min Act: -0.0000

Data Index: 89692 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.8177. Min Act: -0.0000

Data Index: 1290611 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.8056. Min Act: -0.0000

Data Index: 611144 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.8025. Min Act: -0.0000

Data Index: 209674 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.5034. Min Act: -0.0000

Data Index: 1357787 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.7493. Min Act: -0.0000

Data Index: 552334 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 3.3398. Min Range: -3.3398

Max Act: 3.0214. Min Act: -0.0000

Data Index: 1342528 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.7421. Min Act: -0.0000

Data Index: 448723 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 3.3398. Min Range: -3.3398

Max Act: 2.6071. Min Act: -0.0000

Data Index: 172784 (C4 (Web Text))

Max Activating Token Index: 140