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

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

Neuron 150 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3928. Min Act: -0.0000

Data Index: 982468 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.4469. Min Act: -0.0000

Data Index: 838674 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3627. Min Act: -0.0000

Data Index: 409092 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.4818. Min Act: -0.0000

Data Index: 224676 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3962. Min Act: -0.0000

Data Index: 148338 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3632. Min Act: -0.0000

Data Index: 875709 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3514. Min Act: -0.0000

Data Index: 997272 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3876. Min Act: -0.0000

Data Index: 993864 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3914. Min Act: -0.0000

Data Index: 888238 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3533. Min Act: -0.0000

Data Index: 734390 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3795. Min Act: -0.0000

Data Index: 763132 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.4068. Min Act: -0.0000

Data Index: 886656 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3668. Min Act: -0.0000

Data Index: 170370 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2965. Min Act: -0.0000

Data Index: 615067 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3517. Min Act: -0.0000

Data Index: 518750 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3057. Min Act: -0.0000

Data Index: 684382 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3359. Min Act: -0.0000

Data Index: 103392 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3683. Min Act: -0.0000

Data Index: 251333 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2957. Min Act: -0.0000

Data Index: 799418 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2704. Min Act: -0.0000

Data Index: 437317 (C4 (Web Text))

Max Activating Token Index: 115