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

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

Neuron 700 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.4385. Min Act: -0.0000

Data Index: 589541 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.4233. Min Act: -0.0000

Data Index: 657714 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.5053. Min Act: -0.0000

Data Index: 420961 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.0927. Min Act: -0.0000

Data Index: 451356 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.1358. Min Act: -0.0000

Data Index: 1060641 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.2753. Min Act: -0.0000

Data Index: 771176 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.3849. Min Act: -0.0000

Data Index: 40181 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.1773. Min Act: -0.0000

Data Index: 982539 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 3.5053. Min Range: -3.5053

Max Act: 2.6999. Min Act: -0.0000

Data Index: 992885 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 3.5053. Min Range: -3.5053

Max Act: 2.8473. Min Act: -0.0000

Data Index: 553478 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.0880. Min Act: -0.0000

Data Index: 499430 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.0640. Min Act: -0.0000

Data Index: 669551 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 3.5053. Min Range: -3.5053

Max Act: 2.5244. Min Act: -0.0000

Data Index: 120358 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 3.5053. Min Range: -3.5053

Max Act: 2.9093. Min Act: -0.0000

Data Index: 517562 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 3.5053. Min Range: -3.5053

Max Act: 3.0527. Min Act: -0.0000

Data Index: 1065699 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 3.5053. Min Range: -3.5053

Max Act: 2.9073. Min Act: -0.0000

Data Index: 325853 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 3.5053. Min Range: -3.5053

Max Act: 2.8613. Min Act: -0.0000

Data Index: 290703 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 3.5053. Min Range: -3.5053

Max Act: 2.7082. Min Act: -0.0000

Data Index: 925470 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 3.5053. Min Range: -3.5053

Max Act: 2.9550. Min Act: -0.0000

Data Index: 224638 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 3.5053. Min Range: -3.5053

Max Act: 2.5425. Min Act: -0.0000

Data Index: 1303226 (C4 (Web Text))

Max Activating Token Index: 395