Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 25 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0003

Data Index: 593184 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0331. Min Act: -0.0003

Data Index: 271599 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0321. Min Act: -0.0003

Data Index: 100669 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0335. Min Act: -0.0003

Data Index: 683390 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0311. Min Act: -0.0003

Data Index: 974507 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0313. Min Act: -0.0003

Data Index: 879208 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1100576 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0308. Min Act: -0.0003

Data Index: 616081 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0303. Min Act: -0.0003

Data Index: 858047 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0301. Min Act: -0.0004

Data Index: 106121 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1003281 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1007340 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0299. Min Act: -0.0003

Data Index: 242756 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0297. Min Act: -0.0003

Data Index: 53295 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0297. Min Act: -0.0003

Data Index: 775540 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0299. Min Act: -0.0003

Data Index: 67862 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0309. Min Act: -0.0003

Data Index: 932123 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0293. Min Act: -0.0003

Data Index: 116091 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0285. Min Act: -0.0003

Data Index: 468192 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1090820 (C4 (Web Text))

Max Activating Token Index: 619