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

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

Neuron 4063 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.3469. Min Act: -0.0001

Data Index: 666673 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.2564. Min Act: -0.0001

Data Index: 1338408 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.2224. Min Act: -0.0001

Data Index: 575888 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0027. Min Act: -0.0001

Data Index: 900349 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.1680. Min Act: -0.0001

Data Index: 1211954 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.1694. Min Act: -0.0001

Data Index: 1003792 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0878. Min Act: -0.0001

Data Index: 1072211 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0787. Min Act: -0.0001

Data Index: 141592 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0850. Min Act: -0.0001

Data Index: 41995 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0500. Min Act: -0.0001

Data Index: 862299 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0881. Min Act: -0.0001

Data Index: 582077 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0037. Min Act: -0.0001

Data Index: 1324330 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 1.3469. Min Range: -1.3469

Max Act: 0.9704. Min Act: -0.0001

Data Index: 974563 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 1.3469. Min Range: -1.3469

Max Act: 0.9663. Min Act: -0.0001

Data Index: 1125679 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0386. Min Act: -0.0001

Data Index: 739908 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.3469. Min Range: -1.3469

Max Act: 0.9824. Min Act: -0.0001

Data Index: 280620 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0277. Min Act: -0.0001

Data Index: 58014 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.3469. Min Range: -1.3469

Max Act: 0.9387. Min Act: -0.0001

Data Index: 17906 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 1.3469. Min Range: -1.3469

Max Act: 0.9840. Min Act: -0.0001

Data Index: 381536 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 1.3469. Min Range: -1.3469

Max Act: 1.0176. Min Act: -0.0001

Data Index: 1178305 (C4 (Web Text))

Max Activating Token Index: 307