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

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

Neuron 4579 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.6943. Min Act: -0.0000

Data Index: 772211 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.3337. Min Act: -0.0000

Data Index: 708172 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.3501. Min Act: -0.0000

Data Index: 129668 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.3356. Min Act: -0.0000

Data Index: 475717 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.3103. Min Act: -0.0000

Data Index: 107121 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 2.6943. Min Range: -2.6943

Max Act: 1.8740. Min Act: -0.0000

Data Index: 646456 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.2097. Min Act: -0.0000

Data Index: 945705 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.0632. Min Act: -0.0000

Data Index: 336607 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.2120. Min Act: -0.0000

Data Index: 80019 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.1538. Min Act: -0.0000

Data Index: 541142 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 2.6943. Min Range: -2.6943

Max Act: 1.9723. Min Act: -0.0000

Data Index: 327427 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.0828. Min Act: -0.0000

Data Index: 614859 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 2.6943. Min Range: -2.6943

Max Act: 1.9876. Min Act: -0.0000

Data Index: 965873 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 2.6943. Min Range: -2.6943

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1139868 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 2.6943. Min Range: -2.6943

Max Act: 1.9670. Min Act: -0.0000

Data Index: 1134411 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 2.6943. Min Range: -2.6943

Max Act: 2.0798. Min Act: -0.0000

Data Index: 1164834 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 2.6943. Min Range: -2.6943

Max Act: 1.9104. Min Act: -0.0000

Data Index: 625619 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 2.6943. Min Range: -2.6943

Max Act: 1.9292. Min Act: -0.0000

Data Index: 95127 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 2.6943. Min Range: -2.6943

Max Act: 1.8984. Min Act: -0.0000

Data Index: 300440 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 2.6943. Min Range: -2.6943

Max Act: 1.8815. Min Act: -0.0000

Data Index: 896386 (C4 (Web Text))

Max Activating Token Index: 929