Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 384 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0122. Min Act: -0.0006

Data Index: 496430 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0110. Min Act: -0.0006

Data Index: 527180 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0100. Min Act: -0.0006

Data Index: 321265 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0098. Min Act: -0.0006

Data Index: 278012 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1136353 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0094. Min Act: -0.0006

Data Index: 593645 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0092. Min Act: -0.0006

Data Index: 61056 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0091. Min Act: -0.0006

Data Index: 126102 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0090. Min Act: -0.0006

Data Index: 286540 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0091. Min Act: -0.0006

Data Index: 998051 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1180922 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1151798 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0090. Min Act: -0.0006

Data Index: 171566 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0088. Min Act: -0.0006

Data Index: 836470 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0088. Min Act: -0.0005

Data Index: 708109 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0089. Min Act: -0.0006

Data Index: 537530 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0088. Min Act: -0.0006

Data Index: 573614 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0087. Min Act: -0.0007

Data Index: 1136720 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1314756 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0087. Min Act: -0.0007

Data Index: 1122040 (C4 (Web Text))

Max Activating Token Index: 180