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

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

Neuron 2799 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0739. Min Act: -0.0003

Data Index: 795314 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0652. Min Act: -0.0003

Data Index: 520223 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0678. Min Act: -0.0003

Data Index: 969286 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0665. Min Act: -0.0003

Data Index: 550093 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1046609 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0597. Min Act: -0.0003

Data Index: 390124 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0628. Min Act: -0.0003

Data Index: 258709 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0630. Min Act: -0.0003

Data Index: 760587 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1309420 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0624. Min Act: -0.0003

Data Index: 1418896 (Python Code)

Max Activating Token Index: 644

Text #10

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0596. Min Act: -0.0003

Data Index: 60829 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1308725 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0663. Min Act: -0.0003

Data Index: 754436 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1358322 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1218931 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0658. Min Act: -0.0003

Data Index: 400993 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0622. Min Act: -0.0003

Data Index: 127712 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0622. Min Act: -0.0003

Data Index: 633717 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0643. Min Act: -0.0003

Data Index: 234941 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0554. Min Act: -0.0003

Data Index: 344771 (C4 (Web Text))

Max Activating Token Index: 873