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

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

Neuron 1169 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1697. Min Range: -2.1697

Max Act: 2.1697. Min Act: -0.0000

Data Index: 209563 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 2.1697. Min Range: -2.1697

Max Act: 2.0448. Min Act: -0.0000

Data Index: 378272 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 2.1697. Min Range: -2.1697

Max Act: 2.0144. Min Act: -0.0000

Data Index: 1081940 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.9145. Min Act: -0.0000

Data Index: 601477 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.9156. Min Act: -0.0000

Data Index: 475712 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.8671. Min Act: -0.0000

Data Index: 274530 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.7128. Min Act: -0.0000

Data Index: 999362 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.8256. Min Act: -0.0000

Data Index: 18333 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.8202. Min Act: -0.0000

Data Index: 1146136 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.8122. Min Act: -0.0000

Data Index: 697550 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.5291. Min Act: -0.0000

Data Index: 1042753 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.6940. Min Act: -0.0000

Data Index: 1315341 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.7873. Min Act: -0.0000

Data Index: 1255179 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.7438. Min Act: -0.0000

Data Index: 339000 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.7128. Min Act: -0.0000

Data Index: 784398 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.6881. Min Act: -0.0000

Data Index: 166384 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.7008. Min Act: -0.0000

Data Index: 399677 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.6920. Min Act: -0.0000

Data Index: 787099 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.6817. Min Act: -0.0000

Data Index: 697272 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 2.1697. Min Range: -2.1697

Max Act: 1.6593. Min Act: -0.0000

Data Index: 702017 (C4 (Web Text))

Max Activating Token Index: 646