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

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

Neuron 4992 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.7995. Min Act: -0.0001

Data Index: 409364 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.7366. Min Act: -0.0001

Data Index: 968833 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.6536. Min Act: -0.0001

Data Index: 1237337 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.6301. Min Act: -0.0001

Data Index: 221362 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.5583. Min Act: -0.0001

Data Index: 715895 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.6600. Min Act: -0.0001

Data Index: 183732 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.4386. Min Act: -0.0001

Data Index: 755579 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.5132. Min Act: -0.0001

Data Index: 199676 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.4785. Min Act: -0.0001

Data Index: 664266 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.5339. Min Act: -0.0001

Data Index: 447231 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.3957. Min Act: -0.0001

Data Index: 1100695 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.5311. Min Act: -0.0001

Data Index: 335884 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.4122. Min Act: -0.0001

Data Index: 1357126 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.3138. Min Act: -0.0001

Data Index: 21751 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.2932. Min Act: -0.0001

Data Index: 346944 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.3424. Min Act: -0.0001

Data Index: 1298936 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.3597. Min Act: -0.0001

Data Index: 552992 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.2868. Min Act: -0.0001

Data Index: 288160 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.3610. Min Act: -0.0001

Data Index: 1058473 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.7995. Min Range: -1.7995

Max Act: 1.3740. Min Act: -0.0001

Data Index: 1038774 (C4 (Web Text))

Max Activating Token Index: 559