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

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

Neuron 1862 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.4047. Min Act: -0.0003

Data Index: 1254836 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3840. Min Act: -0.0003

Data Index: 590583 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3833. Min Act: -0.0002

Data Index: 265793 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3641. Min Act: -0.0003

Data Index: 1007405 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3426. Min Act: -0.0003

Data Index: 982676 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3485. Min Act: -0.0003

Data Index: 1267858 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3504. Min Act: -0.0003

Data Index: 1075074 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3446. Min Act: -0.0003

Data Index: 872157 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3321. Min Act: -0.0003

Data Index: 971970 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3470. Min Act: -0.0003

Data Index: 75759 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3344. Min Act: -0.0003

Data Index: 310111 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3200. Min Act: -0.0003

Data Index: 305425 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3256. Min Act: -0.0003

Data Index: 1354538 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3354. Min Act: -0.0003

Data Index: 234476 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3221. Min Act: -0.0003

Data Index: 177916 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.2948. Min Act: -0.0003

Data Index: 7193 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3002. Min Act: -0.0003

Data Index: 1272076 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3073. Min Act: -0.0003

Data Index: 1321102 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.2976. Min Act: -0.0003

Data Index: 1334665 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.4047. Min Range: -0.4047

Max Act: 0.3065. Min Act: -0.0003

Data Index: 222576 (C4 (Web Text))

Max Activating Token Index: 665