Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 80 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.7114. Min Act: -0.0001

Data Index: 610939 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.6970. Min Act: -0.0001

Data Index: 971754 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.6448. Min Act: -0.0001

Data Index: 885746 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.6678. Min Act: -0.0001

Data Index: 840901 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.6375. Min Act: -0.0001

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.6216. Min Act: -0.0001

Data Index: 608403 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5732. Min Act: -0.0001

Data Index: 657934 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.6618. Min Act: -0.0001

Data Index: 991094 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5870. Min Act: -0.0001

Data Index: 980675 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.6682. Min Act: -0.0001

Data Index: 600855 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5838. Min Act: -0.0001

Data Index: 931532 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5633. Min Act: -0.0001

Data Index: 584661 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5620. Min Act: -0.0001

Data Index: 356235 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5888. Min Act: -0.0001

Data Index: 462668 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5513. Min Act: -0.0001

Data Index: 357701 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5983. Min Act: -0.0001

Data Index: 645743 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5485. Min Act: -0.0001

Data Index: 89283 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5646. Min Act: -0.0001

Data Index: 622643 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5782. Min Act: -0.0001

Data Index: 858480 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5472. Min Act: -0.0001

Data Index: 312277 (C4 (Web Text))

Max Activating Token Index: 641