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

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

Neuron 2313 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: 3.9790. Min Range: -3.9790

Max Act: 3.9790. Min Act: -0.0000

Data Index: 524818 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 3.9790. Min Range: -3.9790

Max Act: 3.4573. Min Act: -0.0000

Data Index: 148630 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 3.9790. Min Range: -3.9790

Max Act: 3.3359. Min Act: -0.0000

Data Index: 893580 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 3.9790. Min Range: -3.9790

Max Act: 3.0476. Min Act: -0.0000

Data Index: 1320815 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 3.9790. Min Range: -3.9790

Max Act: 3.1663. Min Act: -0.0000

Data Index: 541883 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.9798. Min Act: -0.0000

Data Index: 2510 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 3.9790. Min Range: -3.9790

Max Act: 3.0222. Min Act: -0.0000

Data Index: 456162 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 3.9790. Min Range: -3.9790

Max Act: 3.1511. Min Act: -0.0000

Data Index: 569240 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.8134. Min Act: -0.0000

Data Index: 654951 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.8842. Min Act: -0.0000

Data Index: 752091 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.8586. Min Act: -0.0000

Data Index: 551555 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.7092. Min Act: -0.0000

Data Index: 1197849 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.9499. Min Act: -0.0000

Data Index: 1351575 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.8058. Min Act: -0.0000

Data Index: 708600 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.7946. Min Act: -0.0000

Data Index: 159453 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.9081. Min Act: -0.0000

Data Index: 630099 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.7433. Min Act: -0.0000

Data Index: 354637 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.5513. Min Act: -0.0000

Data Index: 37496 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.6718. Min Act: -0.0000

Data Index: 1012587 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 3.9790. Min Range: -3.9790

Max Act: 2.7941. Min Act: -0.0000

Data Index: 110475 (C4 (Web Text))

Max Activating Token Index: 107