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

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

Neuron 4842 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.5294. Min Act: -0.0000

Data Index: 813082 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.0984. Min Act: -0.0000

Data Index: 1183918 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.1775. Min Act: -0.0000

Data Index: 663196 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.0802. Min Act: -0.0000

Data Index: 1195070 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.0640. Min Act: -0.0000

Data Index: 940811 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.9482. Min Act: -0.0000

Data Index: 629418 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.8569. Min Act: -0.0000

Data Index: 40856 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.9451. Min Act: -0.0000

Data Index: 225379 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.9262. Min Act: -0.0000

Data Index: 273611 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.9254. Min Act: -0.0000

Data Index: 597125 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.9291. Min Act: -0.0001

Data Index: 678654 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.7939. Min Act: -0.0000

Data Index: 1180310 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.8924. Min Act: -0.0000

Data Index: 787063 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.7779. Min Act: -0.0000

Data Index: 459032 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.7569. Min Act: -0.0000

Data Index: 403845 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.8458. Min Act: -0.0000

Data Index: 780247 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.8508. Min Act: -0.0000

Data Index: 99979 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.9226. Min Act: -0.0000

Data Index: 1233603 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.8132. Min Act: -0.0000

Data Index: 990025 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 2.5294. Min Range: -2.5294

Max Act: 1.7939. Min Act: -0.0000

Data Index: 893670 (C4 (Web Text))

Max Activating Token Index: 689