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

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

Neuron 2174 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: 1.1893. Min Range: -1.1893

Max Act: 1.1893. Min Act: -0.0002

Data Index: 536561 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.1860. Min Act: -0.0001

Data Index: 1346897 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.0405. Min Act: -0.0001

Data Index: 1332813 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9937. Min Act: -0.0001

Data Index: 570825 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.0582. Min Act: -0.0002

Data Index: 227548 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.0046. Min Act: -0.0002

Data Index: 349591 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.0474. Min Act: -0.0001

Data Index: 1289624 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9522. Min Act: -0.0002

Data Index: 86683 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.0107. Min Act: -0.0002

Data Index: 729902 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.0047. Min Act: -0.0001

Data Index: 1284873 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.0034. Min Act: -0.0001

Data Index: 914653 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9944. Min Act: -0.0001

Data Index: 611616 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9717. Min Act: -0.0001

Data Index: 899991 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.0144. Min Act: -0.0002

Data Index: 1330650 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.8877. Min Act: -0.0002

Data Index: 157667 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9955. Min Act: -0.0002

Data Index: 300126 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.0092. Min Act: -0.0001

Data Index: 205036 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9502. Min Act: -0.0002

Data Index: 1101823 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9493. Min Act: -0.0002

Data Index: 560575 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9497. Min Act: -0.0002

Data Index: 368556 (C4 (Web Text))

Max Activating Token Index: 246