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

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

Neuron 2838 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.8965. Min Act: -0.0000

Data Index: 405898 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.8158. Min Act: -0.0001

Data Index: 569549 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7311. Min Act: -0.0000

Data Index: 727155 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7126. Min Act: -0.0000

Data Index: 353196 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6499. Min Act: -0.0001

Data Index: 964391 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6792. Min Act: -0.0000

Data Index: 67654 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6503. Min Act: -0.0000

Data Index: 505256 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5907. Min Act: -0.0001

Data Index: 1113847 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5955. Min Act: -0.0001

Data Index: 261366 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5793. Min Act: -0.0000

Data Index: 640943 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5759. Min Act: -0.0000

Data Index: 766463 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5754. Min Act: -0.0001

Data Index: 1005521 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5583. Min Act: -0.0001

Data Index: 12951 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6042. Min Act: -0.0000

Data Index: 17300 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1312841 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1239744 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5016. Min Act: -0.0001

Data Index: 1077262 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5157. Min Act: -0.0001

Data Index: 768046 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.4872. Min Act: -0.0001

Data Index: 698051 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.4976. Min Act: -0.0000

Data Index: 410866 (C4 (Web Text))

Max Activating Token Index: 888