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

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

Neuron 3812 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.6546. Min Act: -0.0000

Data Index: 36650 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3577. Min Act: -0.0001

Data Index: 1124110 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3794. Min Act: -0.0000

Data Index: 967342 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3404. Min Act: -0.0001

Data Index: 40427 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3332. Min Act: -0.0001

Data Index: 1257649 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3560. Min Act: -0.0001

Data Index: 262922 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3600. Min Act: -0.0000

Data Index: 832281 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3379. Min Act: -0.0000

Data Index: 150406 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3178. Min Act: -0.0001

Data Index: 419320 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3208. Min Act: -0.0000

Data Index: 582214 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3229. Min Act: -0.0001

Data Index: 885582 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.2855. Min Act: -0.0001

Data Index: 704611 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3344. Min Act: -0.0001

Data Index: 310917 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1320558 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3009. Min Act: -0.0001

Data Index: 961077 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3302. Min Act: -0.0001

Data Index: 702269 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.2917. Min Act: -0.0001

Data Index: 799283 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3062. Min Act: -0.0001

Data Index: 919550 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.3100. Min Act: -0.0001

Data Index: 562927 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.6546. Min Range: -0.6546

Max Act: 0.2803. Min Act: -0.0001

Data Index: 575435 (C4 (Web Text))

Max Activating Token Index: 216