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

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

Neuron 2537 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.7668. Min Act: -0.0000

Data Index: 707070 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.6521. Min Act: -0.0000

Data Index: 279465 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.5205. Min Act: -0.0000

Data Index: 125491 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1456330 (Python Code)

Max Activating Token Index: 263

Text #4

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.5568. Min Act: -0.0000

Data Index: 541209 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.5537. Min Act: -0.0000

Data Index: 604722 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4358. Min Act: -0.0000

Data Index: 827529 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1152347 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4531. Min Act: -0.0000

Data Index: 337783 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4700. Min Act: -0.0000

Data Index: 360834 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4257. Min Act: -0.0000

Data Index: 141790 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1049120 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1613463 (Python Code)

Max Activating Token Index: 108

Text #13

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4383. Min Act: -0.0001

Data Index: 1147397 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1637785 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4300. Min Act: -0.0000

Data Index: 593419 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.5120. Min Act: -0.0000

Data Index: 546479 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1265374 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1348150 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.7668. Min Range: -0.7668

Max Act: 0.4497. Min Act: -0.0000

Data Index: 579292 (C4 (Web Text))

Max Activating Token Index: 1005