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

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

Neuron 3132 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: 0.8790. Min Range: -0.8790

Max Act: 0.8790. Min Act: -0.0001

Data Index: 853215 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8444. Min Act: -0.0001

Data Index: 350517 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7235. Min Act: -0.0001

Data Index: 434862 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8708. Min Act: -0.0001

Data Index: 607223 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7898. Min Act: -0.0001

Data Index: 1103441 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7663. Min Act: -0.0001

Data Index: 1348410 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7817. Min Act: -0.0001

Data Index: 115367 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8192. Min Act: -0.0001

Data Index: 1191971 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7635. Min Act: -0.0001

Data Index: 852561 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7443. Min Act: -0.0001

Data Index: 1020095 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7150. Min Act: -0.0001

Data Index: 835283 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7288. Min Act: -0.0001

Data Index: 653068 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8248. Min Act: -0.0001

Data Index: 1039472 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7903. Min Act: -0.0001

Data Index: 1161969 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7577. Min Act: -0.0001

Data Index: 703666 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6908. Min Act: -0.0001

Data Index: 575114 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6750. Min Act: -0.0001

Data Index: 844566 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7675. Min Act: -0.0001

Data Index: 372884 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7246. Min Act: -0.0001

Data Index: 662359 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6661. Min Act: -0.0001

Data Index: 760868 (C4 (Web Text))

Max Activating Token Index: 760