Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2395 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.4548. Min Act: -0.0000

Data Index: 1058040 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.2971. Min Act: -0.0000

Data Index: 307171 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.4123. Min Act: -0.0000

Data Index: 554965 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.2178. Min Act: -0.0000

Data Index: 578879 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.1856. Min Act: -0.0000

Data Index: 453708 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.0197. Min Act: -0.0000

Data Index: 296383 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.2368. Min Act: -0.0000

Data Index: 468921 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.2001. Min Act: -0.0000

Data Index: 147287 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 2.4548. Min Range: -2.4548

Max Act: 1.9765. Min Act: -0.0000

Data Index: 573674 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.1509. Min Act: -0.0000

Data Index: 452501 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.0637. Min Act: -0.0000

Data Index: 1193335 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.2861. Min Act: -0.0000

Data Index: 849728 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 2.4548. Min Range: -2.4548

Max Act: 1.9429. Min Act: -0.0000

Data Index: 481291 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 2.4548. Min Range: -2.4548

Max Act: 1.9307. Min Act: -0.0000

Data Index: 125162 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 2.4548. Min Range: -2.4548

Max Act: 1.9250. Min Act: -0.0000

Data Index: 654867 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 2.4548. Min Range: -2.4548

Max Act: 1.8323. Min Act: -0.0000

Data Index: 1325318 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.0946. Min Act: -0.0000

Data Index: 261684 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 2.4548. Min Range: -2.4548

Max Act: 2.0051. Min Act: -0.0000

Data Index: 832754 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 2.4548. Min Range: -2.4548

Max Act: 1.8938. Min Act: -0.0000

Data Index: 573698 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 2.4548. Min Range: -2.4548

Max Act: 1.9634. Min Act: -0.0000

Data Index: 1195438 (C4 (Web Text))

Max Activating Token Index: 11