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

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

Neuron 4302 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.8045. Min Act: -0.0000

Data Index: 872748 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7178. Min Act: -0.0000

Data Index: 645126 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5923. Min Act: -0.0000

Data Index: 391843 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5915. Min Act: 0.0000

Data Index: 604498 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5612. Min Act: -0.0000

Data Index: 458638 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1093522 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5432. Min Act: -0.0000

Data Index: 961000 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1134116 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5254. Min Act: -0.0000

Data Index: 780523 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5316. Min Act: -0.0000

Data Index: 826257 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4928. Min Act: -0.0000

Data Index: 447634 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1337716 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4928. Min Act: -0.0000

Data Index: 527653 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4770. Min Act: -0.0000

Data Index: 646131 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4467. Min Act: -0.0000

Data Index: 116245 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1150786 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4626. Min Act: -0.0000

Data Index: 134087 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1305618 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1305331 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1351727 (C4 (Web Text))

Max Activating Token Index: 61