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

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

Neuron 5097 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: 3.1277. Min Range: -3.1277

Max Act: 3.1207. Min Act: -0.0000

Data Index: 838177 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 3.1277. Min Range: -3.1277

Max Act: 3.1277. Min Act: -0.0000

Data Index: 1150231 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.8863. Min Act: 0.0002

Data Index: 615480 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.8604. Min Act: 0.0001

Data Index: 682333 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.7999. Min Act: -0.0000

Data Index: 640067 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.6292. Min Act: 0.0001

Data Index: 806961 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.7302. Min Act: 0.0001

Data Index: 659783 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.7399. Min Act: -0.0000

Data Index: 581146 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.6542. Min Act: -0.0000

Data Index: 1326039 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.6275. Min Act: -0.0000

Data Index: 1041675 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.5920. Min Act: -0.0000

Data Index: 1075521 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.6923. Min Act: 0.0001

Data Index: 65975 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.4151. Min Act: 0.0000

Data Index: 1053166 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.5295. Min Act: 0.0000

Data Index: 859757 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.4797. Min Act: -0.0000

Data Index: 896758 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.3403. Min Act: -0.0000

Data Index: 1272648 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.3920. Min Act: -0.0000

Data Index: 479798 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.3821. Min Act: 0.0000

Data Index: 1234766 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.2353. Min Act: -0.0000

Data Index: 1347876 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 3.1277. Min Range: -3.1277

Max Act: 2.3505. Min Act: 0.0002

Data Index: 601283 (C4 (Web Text))

Max Activating Token Index: 780