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

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

Neuron 3062 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.7476. Min Act: -0.0001

Data Index: 1172178 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.7607. Min Act: -0.0001

Data Index: 1019918 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.7554. Min Act: -0.0001

Data Index: 496532 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.6623. Min Act: -0.0001

Data Index: 613436 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.6021. Min Act: -0.0001

Data Index: 546015 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.5495. Min Act: -0.0001

Data Index: 1094131 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.5703. Min Act: -0.0001

Data Index: 577217 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.7444. Min Act: -0.0001

Data Index: 866465 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.7291. Min Act: -0.0001

Data Index: 1411272 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.5878. Min Act: -0.0001

Data Index: 711078 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.6660. Min Act: -0.0001

Data Index: 319511 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.5596. Min Act: -0.0001

Data Index: 513327 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.5432. Min Act: -0.0001

Data Index: 1108838 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.5288. Min Act: -0.0001

Data Index: 415429 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.5077. Min Act: -0.0001

Data Index: 631704 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.5029. Min Act: -0.0001

Data Index: 657369 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.5643. Min Act: -0.0001

Data Index: 471245 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.3892. Min Act: -0.0001

Data Index: 596796 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.3602. Min Act: -0.0001

Data Index: 1054173 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.7607. Min Range: -1.7607

Max Act: 1.3308. Min Act: -0.0001

Data Index: 804661 (C4 (Web Text))

Max Activating Token Index: 323