Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3541 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.1475. Min Range: -2.1475

Max Act: 2.1475. Min Act: -0.0000

Data Index: 756392 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 2.1475. Min Range: -2.1475

Max Act: 2.0732. Min Act: -0.0000

Data Index: 247303 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.9841. Min Act: -0.0001

Data Index: 1288838 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.8634. Min Act: -0.0000

Data Index: 951090 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.8628. Min Act: -0.0000

Data Index: 696473 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.7326. Min Act: -0.0000

Data Index: 401536 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.8685. Min Act: -0.0000

Data Index: 106534 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.7629. Min Act: -0.0000

Data Index: 1343961 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.7535. Min Act: -0.0000

Data Index: 1074370 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.6379. Min Act: -0.0000

Data Index: 592276 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.7139. Min Act: -0.0000

Data Index: 150256 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.6203. Min Act: -0.0001

Data Index: 699522 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.6602. Min Act: -0.0000

Data Index: 116452 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.6539. Min Act: -0.0000

Data Index: 360716 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.6502. Min Act: -0.0001

Data Index: 611910 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.5989. Min Act: -0.0000

Data Index: 184760 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.5900. Min Act: -0.0000

Data Index: 287508 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.5348. Min Act: -0.0000

Data Index: 636866 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.6657. Min Act: -0.0000

Data Index: 246004 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 2.1475. Min Range: -2.1475

Max Act: 1.6202. Min Act: -0.0000

Data Index: 1285747 (C4 (Web Text))

Max Activating Token Index: 276