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

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

Neuron 2946 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0762. Min Act: -0.0004

Data Index: 631879 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.1531. Min Act: -0.0004

Data Index: 124404 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7883. Min Act: -0.0004

Data Index: 1269190 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0253. Min Act: -0.0004

Data Index: 983658 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.1134. Min Act: -0.0004

Data Index: 445499 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0425. Min Act: -0.0004

Data Index: 1019614 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0064. Min Act: -0.0004

Data Index: 1118886 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0545. Min Act: -0.0004

Data Index: 1172758 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9423. Min Act: -0.0004

Data Index: 854623 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9718. Min Act: -0.0004

Data Index: 695069 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0323. Min Act: -0.0004

Data Index: 813168 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0037. Min Act: -0.0004

Data Index: 455605 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9625. Min Act: -0.0004

Data Index: 148541 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9254. Min Act: -0.0004

Data Index: 331175 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8920. Min Act: -0.0004

Data Index: 870754 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8996. Min Act: -0.0004

Data Index: 1279053 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8718. Min Act: -0.0004

Data Index: 22824 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9427. Min Act: -0.0004

Data Index: 1039003 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9443. Min Act: -0.0004

Data Index: 340761 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.9412. Min Act: -0.0004

Data Index: 290801 (C4 (Web Text))

Max Activating Token Index: 63