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

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

Neuron 1272 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.1177. Min Act: -0.0001

Data Index: 188628 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.0618. Min Act: -0.0001

Data Index: 1478439 (Python Code)

Max Activating Token Index: 819

Text #2

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.0935. Min Act: -0.0000

Data Index: 904860 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.1926. Min Act: -0.0000

Data Index: 586023 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.0651. Min Act: -0.0001

Data Index: 582524 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.0864. Min Act: -0.0000

Data Index: 790744 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.0996. Min Act: -0.0000

Data Index: 194868 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.0455. Min Act: -0.0001

Data Index: 553672 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.0336. Min Act: -0.0001

Data Index: 1304345 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.1926. Min Range: -1.1926

Max Act: 0.9913. Min Act: -0.0000

Data Index: 71962 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.1926. Min Range: -1.1926

Max Act: 0.8961. Min Act: -0.0001

Data Index: 668015 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1003586 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 1.1926. Min Range: -1.1926

Max Act: 0.9798. Min Act: -0.0000

Data Index: 635649 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.0117. Min Act: -0.0000

Data Index: 955057 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.1926. Min Range: -1.1926

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1033466 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 1.1926. Min Range: -1.1926

Max Act: 0.9763. Min Act: -0.0000

Data Index: 485825 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 1.1926. Min Range: -1.1926

Max Act: 0.9734. Min Act: -0.0001

Data Index: 1052649 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.1926. Min Range: -1.1926

Max Act: 1.0056. Min Act: -0.0001

Data Index: 317461 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.1926. Min Range: -1.1926

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1294788 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 1.1926. Min Range: -1.1926

Max Act: 0.9083. Min Act: -0.0000

Data Index: 805679 (C4 (Web Text))

Max Activating Token Index: 859