Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3997 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.9869. Min Act: -0.0001

Data Index: 628395 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.3148. Min Act: -0.0000

Data Index: 137373 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.3094. Min Act: -0.0000

Data Index: 989334 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.1596. Min Act: -0.0001

Data Index: 229563 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.2713. Min Act: -0.0000

Data Index: 453987 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.1421. Min Act: -0.0001

Data Index: 885090 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.2197. Min Act: -0.0001

Data Index: 598246 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.1898. Min Act: -0.0000

Data Index: 21660 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.0722. Min Act: -0.0000

Data Index: 443339 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.0502. Min Act: -0.0000

Data Index: 1341967 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.0100. Min Act: -0.0001

Data Index: 297392 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 2.9869. Min Range: -2.9869

Max Act: 1.8630. Min Act: -0.0001

Data Index: 1174569 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 2.9869. Min Range: -2.9869

Max Act: 2.1771. Min Act: -0.0001

Data Index: 863125 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 2.9869. Min Range: -2.9869

Max Act: 1.9668. Min Act: -0.0001

Data Index: 905033 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 2.9869. Min Range: -2.9869

Max Act: 1.9534. Min Act: -0.0001

Data Index: 1157907 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 2.9869. Min Range: -2.9869

Max Act: 1.9542. Min Act: -0.0000

Data Index: 756542 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 2.9869. Min Range: -2.9869

Max Act: 1.9527. Min Act: -0.0001

Data Index: 330735 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 2.9869. Min Range: -2.9869

Max Act: 1.8638. Min Act: -0.0000

Data Index: 779609 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 2.9869. Min Range: -2.9869

Max Act: 1.9642. Min Act: -0.0000

Data Index: 1007704 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 2.9869. Min Range: -2.9869

Max Act: 1.8578. Min Act: -0.0001

Data Index: 204648 (C4 (Web Text))

Max Activating Token Index: 80