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

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

Neuron 1273 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: 0.7813. Min Range: -0.7813

Max Act: 0.7813. Min Act: -0.0001

Data Index: 697244 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7627. Min Act: -0.0001

Data Index: 148695 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7456. Min Act: -0.0001

Data Index: 974686 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.7115. Min Act: -0.0001

Data Index: 608585 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.6703. Min Act: -0.0001

Data Index: 885089 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.6655. Min Act: -0.0001

Data Index: 177861 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.6625. Min Act: -0.0001

Data Index: 992841 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1112673 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.6060. Min Act: -0.0001

Data Index: 656842 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.6022. Min Act: -0.0001

Data Index: 1122743 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.6149. Min Act: -0.0001

Data Index: 631570 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.5956. Min Act: -0.0001

Data Index: 377718 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.5840. Min Act: -0.0001

Data Index: 388023 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.5966. Min Act: -0.0001

Data Index: 580103 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.5724. Min Act: -0.0001

Data Index: 60256 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.5688. Min Act: -0.0001

Data Index: 1137509 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.5403. Min Act: -0.0001

Data Index: 810583 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.5494. Min Act: -0.0001

Data Index: 91948 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.5204. Min Act: -0.0001

Data Index: 576500 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.7813. Min Range: -0.7813

Max Act: 0.5019. Min Act: -0.0001

Data Index: 991413 (C4 (Web Text))

Max Activating Token Index: 707