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

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

Neuron 4039 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: 0.8120. Min Range: -0.8120

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1351235 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.8120. Min Act: -0.0000

Data Index: 214617 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1227065 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7729. Min Act: -0.0000

Data Index: 672729 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7626. Min Act: -0.0000

Data Index: 596250 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7451. Min Act: -0.0000

Data Index: 984022 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7189. Min Act: -0.0000

Data Index: 245322 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7059. Min Act: -0.0000

Data Index: 579601 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7390. Min Act: -0.0000

Data Index: 551829 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7203. Min Act: -0.0000

Data Index: 363232 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6943. Min Act: -0.0000

Data Index: 450315 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7399. Min Act: -0.0000

Data Index: 968017 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7009. Min Act: -0.0000

Data Index: 464768 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7001. Min Act: -0.0000

Data Index: 425227 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6759. Min Act: -0.0000

Data Index: 857200 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1054450 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6936. Min Act: -0.0000

Data Index: 432127 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6323. Min Act: -0.0000

Data Index: 625770 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1096269 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1003366 (C4 (Web Text))

Max Activating Token Index: 281