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

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

Neuron 1827 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1302088 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2584. Min Act: -0.0000

Data Index: 552524 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2636. Min Act: -0.0000

Data Index: 641995 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2889. Min Act: -0.0000

Data Index: 98233 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2262. Min Act: -0.0000

Data Index: 625613 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2869. Min Act: -0.0000

Data Index: 16290 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1216973 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2332. Min Act: -0.0000

Data Index: 566453 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2718. Min Act: -0.0000

Data Index: 493817 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2420. Min Act: -0.0000

Data Index: 708929 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2656. Min Act: -0.0000

Data Index: 626626 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1176204 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2541. Min Act: -0.0000

Data Index: 309736 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1094788 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2476. Min Act: -0.0000

Data Index: 116869 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2163. Min Act: -0.0000

Data Index: 652755 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2659. Min Act: -0.0000

Data Index: 854758 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2549. Min Act: -0.0000

Data Index: 480421 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2436. Min Act: -0.0000

Data Index: 103817 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2883. Min Act: -0.0000

Data Index: 25964 (C4 (Web Text))

Max Activating Token Index: 980