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

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

Neuron 3669 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.4810. Min Act: -0.0000

Data Index: 1217503 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.2769. Min Act: -0.0000

Data Index: 1083683 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 2.4810. Min Range: -2.4810

Max Act: 2.1235. Min Act: -0.0000

Data Index: 217152 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7771. Min Act: -0.0000

Data Index: 304856 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7453. Min Act: -0.0000

Data Index: 266029 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7903. Min Act: -0.0000

Data Index: 1097726 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.7672. Min Act: -0.0000

Data Index: 515991 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.6763. Min Act: -0.0000

Data Index: 1116737 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.9751. Min Act: -0.0000

Data Index: 545234 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.5231. Min Act: -0.0000

Data Index: 1230200 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.4579. Min Act: -0.0000

Data Index: 1191378 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.5243. Min Act: -0.0000

Data Index: 747099 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.5659. Min Act: -0.0000

Data Index: 34427 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.6190. Min Act: -0.0000

Data Index: 490209 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.4568. Min Act: -0.0000

Data Index: 894273 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.4963. Min Act: -0.0000

Data Index: 883283 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.5625. Min Act: -0.0000

Data Index: 1208163 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.5665. Min Act: -0.0000

Data Index: 436664 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.5033. Min Act: -0.0000

Data Index: 340396 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 2.4810. Min Range: -2.4810

Max Act: 1.4033. Min Act: -0.0000

Data Index: 333957 (C4 (Web Text))

Max Activating Token Index: 908