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

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

Neuron 2783 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: 4.2975. Min Range: -4.2975

Max Act: 4.2975. Min Act: -0.0001

Data Index: 431097 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 4.2975. Min Range: -4.2975

Max Act: 3.9618. Min Act: -0.0001

Data Index: 430823 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 4.2975. Min Range: -4.2975

Max Act: 3.5203. Min Act: -0.0000

Data Index: 1324248 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 4.2975. Min Range: -4.2975

Max Act: 3.3751. Min Act: -0.0001

Data Index: 75456 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 4.2975. Min Range: -4.2975

Max Act: 3.3617. Min Act: -0.0001

Data Index: 903280 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 4.2975. Min Range: -4.2975

Max Act: 3.1628. Min Act: -0.0001

Data Index: 785492 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 4.2975. Min Range: -4.2975

Max Act: 3.2597. Min Act: -0.0001

Data Index: 972364 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 4.2975. Min Range: -4.2975

Max Act: 3.5109. Min Act: -0.0001

Data Index: 725534 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.9913. Min Act: -0.0001

Data Index: 1066624 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.8475. Min Act: -0.0001

Data Index: 968661 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 4.2975. Min Range: -4.2975

Max Act: 3.2394. Min Act: -0.0001

Data Index: 941169 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.8158. Min Act: -0.0001

Data Index: 1357414 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.7543. Min Act: -0.0000

Data Index: 766017 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.7352. Min Act: -0.0001

Data Index: 794676 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.3626. Min Act: -0.0000

Data Index: 1192563 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.6827. Min Act: -0.0001

Data Index: 409745 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.5334. Min Act: -0.0001

Data Index: 24660 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.6588. Min Act: -0.0001

Data Index: 663096 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.7175. Min Act: -0.0001

Data Index: 737951 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 4.2975. Min Range: -4.2975

Max Act: 2.4916. Min Act: -0.0001

Data Index: 153147 (C4 (Web Text))

Max Activating Token Index: 679