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

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

Neuron 172 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: 0.2873. Min Range: -0.2873

Max Act: 0.2873. Min Act: -0.0001

Data Index: 586906 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2640. Min Act: -0.0001

Data Index: 610906 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2472. Min Act: -0.0001

Data Index: 201120 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2385. Min Act: -0.0001

Data Index: 1471573 (Python Code)

Max Activating Token Index: 59

Text #4

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2288. Min Act: -0.0000

Data Index: 430215 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1252083 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2243. Min Act: -0.0001

Data Index: 1251198 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2181. Min Act: -0.0001

Data Index: 168005 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2010. Min Act: -0.0001

Data Index: 1003830 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2021. Min Act: -0.0001

Data Index: 1121864 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2475. Min Act: -0.0001

Data Index: 942134 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1898. Min Act: -0.0001

Data Index: 980293 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1791. Min Act: -0.0001

Data Index: 841257 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1982. Min Act: -0.0000

Data Index: 831343 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1843. Min Act: -0.0001

Data Index: 215534 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1060224 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1844. Min Act: -0.0001

Data Index: 1243595 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1610551 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1454862 (Python Code)

Max Activating Token Index: 174

Text #19

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1037186 (C4 (Web Text))

Max Activating Token Index: 125