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

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

Neuron 353 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2733. Min Act: -0.0001

Data Index: 440080 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2425. Min Act: -0.0001

Data Index: 594383 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2406. Min Act: -0.0001

Data Index: 302309 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2354. Min Act: -0.0001

Data Index: 412471 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2333. Min Act: -0.0001

Data Index: 104228 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2143. Min Act: -0.0001

Data Index: 1062851 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1221949 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2055. Min Act: -0.0001

Data Index: 376007 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2083. Min Act: -0.0001

Data Index: 466005 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1997. Min Act: -0.0001

Data Index: 48748 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1949. Min Act: -0.0001

Data Index: 840117 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2017. Min Act: -0.0001

Data Index: 526739 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1161459 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2044. Min Act: -0.0001

Data Index: 773449 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1981. Min Act: -0.0001

Data Index: 1332357 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1979. Min Act: -0.0001

Data Index: 123831 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1262288 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1890. Min Act: -0.0001

Data Index: 625749 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.1957. Min Act: -0.0001

Data Index: 658289 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.2733. Min Range: -0.2733

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1186188 (C4 (Web Text))

Max Activating Token Index: 365