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

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

Neuron 2568 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.3915. Min Act: -0.0001

Data Index: 371341 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.1061. Min Act: -0.0001

Data Index: 757596 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9556. Min Act: -0.0001

Data Index: 622413 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.0520. Min Act: -0.0001

Data Index: 276998 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.0072. Min Act: -0.0001

Data Index: 1017605 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.0334. Min Act: -0.0001

Data Index: 579073 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.0014. Min Act: -0.0001

Data Index: 434535 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 1.3915. Min Range: -1.3915

Max Act: 1.0274. Min Act: -0.0001

Data Index: 511362 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9513. Min Act: -0.0001

Data Index: 857756 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9733. Min Act: -0.0001

Data Index: 1307711 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9471. Min Act: -0.0001

Data Index: 442964 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9423. Min Act: -0.0001

Data Index: 334225 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9601. Min Act: -0.0001

Data Index: 570447 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9580. Min Act: -0.0001

Data Index: 601139 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.8930. Min Act: -0.0001

Data Index: 1195829 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.8773. Min Act: -0.0001

Data Index: 746460 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9398. Min Act: -0.0001

Data Index: 41766 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.8830. Min Act: -0.0001

Data Index: 426046 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9286. Min Act: -0.0001

Data Index: 1115893 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 1.3915. Min Range: -1.3915

Max Act: 0.9119. Min Act: -0.0001

Data Index: 1151365 (C4 (Web Text))

Max Activating Token Index: 603