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

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

Neuron 4746 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.5771. Min Act: -0.0000

Data Index: 444610 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.3854. Min Act: -0.0000

Data Index: 282963 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.2193. Min Act: -0.0000

Data Index: 1105185 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.7878. Min Act: -0.0000

Data Index: 874711 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.7709. Min Act: -0.0000

Data Index: 1073018 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.6707. Min Act: -0.0000

Data Index: 648529 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.6065. Min Act: -0.0000

Data Index: 395807 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.5566. Min Act: -0.0000

Data Index: 1064661 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.5512. Min Act: -0.0000

Data Index: 1295086 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.5352. Min Act: -0.0000

Data Index: 142215 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.5189. Min Act: -0.0000

Data Index: 443456 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.4939. Min Act: -0.0000

Data Index: 608383 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.4983. Min Act: -0.0000

Data Index: 652634 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.4735. Min Act: -0.0000

Data Index: 892477 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.4695. Min Act: -0.0000

Data Index: 1054565 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.4713. Min Act: -0.0000

Data Index: 462662 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.5942. Min Act: -0.0000

Data Index: 800684 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.5739. Min Act: -0.0000

Data Index: 51062 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.4655. Min Act: -0.0000

Data Index: 679660 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 3.5771. Min Range: -3.5771

Max Act: 2.5915. Min Act: -0.0000

Data Index: 452412 (C4 (Web Text))

Max Activating Token Index: 964