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

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

Neuron 2882 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5609. Min Range: -1.5609

Max Act: 1.5609. Min Act: -0.0002

Data Index: 1085513 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.9909. Min Act: -0.0002

Data Index: 757306 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8766. Min Act: -0.0002

Data Index: 453808 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8781. Min Act: -0.0002

Data Index: 119508 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.7959. Min Act: -0.0002

Data Index: 498705 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8659. Min Act: -0.0002

Data Index: 468039 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8589. Min Act: -0.0002

Data Index: 599979 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8434. Min Act: -0.0002

Data Index: 81272 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8191. Min Act: -0.0002

Data Index: 112104 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8808. Min Act: -0.0002

Data Index: 430388 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8683. Min Act: -0.0002

Data Index: 153559 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.7126. Min Act: -0.0002

Data Index: 345511 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.7732. Min Act: -0.0002

Data Index: 68909 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8312. Min Act: -0.0002

Data Index: 890299 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8420. Min Act: -0.0002

Data Index: 220506 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.7987. Min Act: -0.0002

Data Index: 182115 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.8021. Min Act: -0.0002

Data Index: 419647 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.6632. Min Act: -0.0002

Data Index: 1221109 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.7712. Min Act: -0.0002

Data Index: 951911 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.5609. Min Range: -1.5609

Max Act: 0.7658. Min Act: -0.0002

Data Index: 44517 (C4 (Web Text))

Max Activating Token Index: 440