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

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

Neuron 672 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1134465 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.6821. Min Act: -0.0000

Data Index: 428105 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.6120. Min Act: -0.0000

Data Index: 397270 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5967. Min Act: -0.0000

Data Index: 97128 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5804. Min Act: -0.0000

Data Index: 434171 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5830. Min Act: -0.0000

Data Index: 303178 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4918. Min Act: -0.0000

Data Index: 556347 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5147. Min Act: -0.0000

Data Index: 939741 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.5161. Min Act: -0.0000

Data Index: 354993 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1143507 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4404. Min Act: -0.0000

Data Index: 63594 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4681. Min Act: -0.0000

Data Index: 472129 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4786. Min Act: -0.0000

Data Index: 362874 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4547. Min Act: -0.0000

Data Index: 63482 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4748. Min Act: -0.0000

Data Index: 594585 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4171. Min Act: -0.0000

Data Index: 38816 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4413. Min Act: -0.0000

Data Index: 310663 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4617. Min Act: -0.0000

Data Index: 933506 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4457. Min Act: -0.0000

Data Index: 831650 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.7184. Min Range: -0.7184

Max Act: 0.4485. Min Act: 0.0000

Data Index: 1106167 (C4 (Web Text))

Max Activating Token Index: 157