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

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

Neuron 2566 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: 1.0850. Min Range: -1.0850

Max Act: 1.0850. Min Act: -0.0001

Data Index: 433292 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8699. Min Act: -0.0001

Data Index: 1036826 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8249. Min Act: -0.0001

Data Index: 1237156 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7916. Min Act: -0.0001

Data Index: 35321 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7750. Min Act: -0.0001

Data Index: 1141682 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8351. Min Act: -0.0001

Data Index: 1180014 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1357355 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8592. Min Act: -0.0001

Data Index: 1331441 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8043. Min Act: -0.0001

Data Index: 51898 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8040. Min Act: -0.0001

Data Index: 573819 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7688. Min Act: -0.0001

Data Index: 656153 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7125. Min Act: -0.0001

Data Index: 405842 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7630. Min Act: -0.0001

Data Index: 391872 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7158. Min Act: -0.0000

Data Index: 382676 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1283384 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7482. Min Act: -0.0001

Data Index: 905937 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.8202. Min Act: -0.0001

Data Index: 488412 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7670. Min Act: -0.0001

Data Index: 844025 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7463. Min Act: -0.0000

Data Index: 287467 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.0850. Min Range: -1.0850

Max Act: 0.7634. Min Act: -0.0001

Data Index: 327067 (C4 (Web Text))

Max Activating Token Index: 28