Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 369 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.2033. Min Act: -0.0000

Data Index: 964295 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.1918. Min Act: -0.0000

Data Index: 630433 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0739. Min Act: -0.0000

Data Index: 995834 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.1184. Min Act: -0.0000

Data Index: 165724 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0914. Min Act: -0.0000

Data Index: 627203 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0441. Min Act: -0.0000

Data Index: 922957 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.9821. Min Act: -0.0000

Data Index: 101035 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.1058. Min Act: -0.0000

Data Index: 1208101 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0434. Min Act: 0.0001

Data Index: 1262498 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0313. Min Act: -0.0000

Data Index: 154257 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0382. Min Act: -0.0000

Data Index: 681485 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1002092 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1233547 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0152. Min Act: -0.0000

Data Index: 200254 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0214. Min Act: -0.0000

Data Index: 655734 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0798. Min Act: -0.0000

Data Index: 309196 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0687. Min Act: -0.0000

Data Index: 795786 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.9989. Min Act: 0.0001

Data Index: 190103 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0049. Min Act: 0.0001

Data Index: 960584 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.2033. Min Range: -1.2033

Max Act: 1.0601. Min Act: -0.0000

Data Index: 171272 (C4 (Web Text))

Max Activating Token Index: 711