Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2568 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8939. Min Act: -0.0001

Data Index: 757349 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8829. Min Act: -0.0001

Data Index: 854629 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8534. Min Act: -0.0001

Data Index: 323753 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8637. Min Act: -0.0001

Data Index: 441889 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7830. Min Act: -0.0001

Data Index: 372038 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8264. Min Act: -0.0001

Data Index: 549796 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8172. Min Act: -0.0001

Data Index: 1345002 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8373. Min Act: -0.0001

Data Index: 64172 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8135. Min Act: -0.0001

Data Index: 629547 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8609. Min Act: -0.0001

Data Index: 902111 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8068. Min Act: -0.0001

Data Index: 661855 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7760. Min Act: -0.0001

Data Index: 906369 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.8195. Min Act: -0.0001

Data Index: 1029578 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7664. Min Act: -0.0001

Data Index: 982155 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7524. Min Act: -0.0001

Data Index: 1157507 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7589. Min Act: -0.0001

Data Index: 850569 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7140. Min Act: -0.0001

Data Index: 1093568 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7148. Min Act: -0.0001

Data Index: 238756 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7872. Min Act: -0.0001

Data Index: 753117 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.8939. Min Range: -0.8939

Max Act: 0.7121. Min Act: -0.0001

Data Index: 279718 (C4 (Web Text))

Max Activating Token Index: 951