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

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

Neuron 3395 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: 2.0386. Min Range: -2.0386

Max Act: 2.0372. Min Act: -0.0000

Data Index: 831993 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 2.0386. Min Range: -2.0386

Max Act: 2.0060. Min Act: -0.0001

Data Index: 4406 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.9961. Min Act: -0.0000

Data Index: 67103 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 2.0386. Min Range: -2.0386

Max Act: 2.0386. Min Act: -0.0000

Data Index: 1142693 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.9178. Min Act: -0.0000

Data Index: 360602 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.8659. Min Act: -0.0000

Data Index: 367648 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.8085. Min Act: -0.0000

Data Index: 831750 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.6931. Min Act: -0.0001

Data Index: 1161647 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.8899. Min Act: -0.0000

Data Index: 655502 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1163907 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.4737. Min Act: -0.0000

Data Index: 306985 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.7297. Min Act: -0.0001

Data Index: 784028 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.7050. Min Act: -0.0000

Data Index: 837296 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.5287. Min Act: -0.0000

Data Index: 472404 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.7119. Min Act: -0.0000

Data Index: 964261 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.7935. Min Act: -0.0000

Data Index: 434845 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.6034. Min Act: -0.0000

Data Index: 932689 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.6789. Min Act: -0.0000

Data Index: 979781 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.6743. Min Act: -0.0000

Data Index: 1118891 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 2.0386. Min Range: -2.0386

Max Act: 1.7670. Min Act: -0.0000

Data Index: 721243 (C4 (Web Text))

Max Activating Token Index: 444