Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 72 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8831. Min Range: -3.8831

Max Act: 3.8831. Min Act: -0.0000

Data Index: 605739 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 3.8831. Min Range: -3.8831

Max Act: 3.1287. Min Act: -0.0000

Data Index: 151097 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 3.8831. Min Range: -3.8831

Max Act: 3.5214. Min Act: -0.0000

Data Index: 271074 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 3.8831. Min Range: -3.8831

Max Act: 3.0217. Min Act: -0.0000

Data Index: 813931 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.9053. Min Act: -0.0000

Data Index: 294721 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.8326. Min Act: -0.0000

Data Index: 1069908 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 3.8831. Min Range: -3.8831

Max Act: 3.0740. Min Act: -0.0000

Data Index: 180608 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 3.8831. Min Range: -3.8831

Max Act: 3.0705. Min Act: -0.0000

Data Index: 319368 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 3.8831. Min Range: -3.8831

Max Act: 3.1712. Min Act: -0.0000

Data Index: 813322 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.6530. Min Act: -0.0000

Data Index: 1040179 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.6416. Min Act: -0.0000

Data Index: 379059 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.6516. Min Act: -0.0000

Data Index: 832523 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.7647. Min Act: -0.0000

Data Index: 685037 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.8351. Min Act: -0.0000

Data Index: 1115428 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.6902. Min Act: -0.0000

Data Index: 223060 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.5419. Min Act: -0.0000

Data Index: 55338 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.6667. Min Act: -0.0000

Data Index: 169331 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.2663. Min Act: -0.0000

Data Index: 883418 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.5177. Min Act: -0.0000

Data Index: 701994 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 3.8831. Min Range: -3.8831

Max Act: 2.2227. Min Act: -0.0000

Data Index: 749207 (C4 (Web Text))

Max Activating Token Index: 203