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

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

Neuron 342 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1248172 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2469. Min Act: -0.0000

Data Index: 963539 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2369. Min Act: -0.0000

Data Index: 294510 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2300. Min Act: -0.0000

Data Index: 937706 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2240. Min Act: -0.0001

Data Index: 650328 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2170. Min Act: -0.0001

Data Index: 186412 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2336. Min Act: -0.0000

Data Index: 435658 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2159. Min Act: -0.0001

Data Index: 275307 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1068716 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2066. Min Act: -0.0000

Data Index: 649674 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2002. Min Act: -0.0000

Data Index: 558800 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1113664 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2012. Min Act: -0.0001

Data Index: 997167 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1256705 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1911. Min Act: -0.0001

Data Index: 442256 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1912. Min Act: -0.0001

Data Index: 1345725 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1918. Min Act: -0.0000

Data Index: 745193 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1958. Min Act: -0.0000

Data Index: 778421 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1896. Min Act: -0.0001

Data Index: 1333894 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1897. Min Act: -0.0000

Data Index: 831718 (C4 (Web Text))

Max Activating Token Index: 1022