Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4042 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5262. Min Act: -0.0001

Data Index: 800324 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5502. Min Act: -0.0001

Data Index: 861369 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5724. Min Act: -0.0001

Data Index: 1157435 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5534. Min Act: -0.0001

Data Index: 1085879 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5428. Min Act: -0.0001

Data Index: 231444 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5525. Min Act: -0.0001

Data Index: 306773 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4634. Min Act: -0.0001

Data Index: 335741 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5224. Min Act: -0.0002

Data Index: 141220 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5386. Min Act: -0.0002

Data Index: 764455 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1321394 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4828. Min Act: -0.0002

Data Index: 1064471 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4965. Min Act: -0.0001

Data Index: 749495 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5110. Min Act: -0.0001

Data Index: 114104 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4813. Min Act: -0.0002

Data Index: 504152 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4898. Min Act: -0.0001

Data Index: 1267584 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4916. Min Act: -0.0002

Data Index: 318249 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4749. Min Act: -0.0001

Data Index: 486621 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4750. Min Act: -0.0002

Data Index: 925609 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4849. Min Act: -0.0002

Data Index: 612418 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4538. Min Act: -0.0001

Data Index: 1249133 (C4 (Web Text))

Max Activating Token Index: 50