Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2197 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2889. Min Act: -0.0001

Data Index: 1321304 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2495. Min Act: -0.0001

Data Index: 208971 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2553. Min Act: -0.0001

Data Index: 869233 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2288. Min Act: -0.0001

Data Index: 214831 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2301. Min Act: -0.0001

Data Index: 233120 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2276. Min Act: -0.0001

Data Index: 1247054 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1020557 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1841. Min Act: -0.0001

Data Index: 730994 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2244. Min Act: -0.0001

Data Index: 681371 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2147. Min Act: -0.0001

Data Index: 366898 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2128. Min Act: -0.0001

Data Index: 584432 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2063. Min Act: -0.0001

Data Index: 371345 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2158. Min Act: -0.0001

Data Index: 368591 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2036. Min Act: -0.0001

Data Index: 573839 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1915. Min Act: -0.0001

Data Index: 78885 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2031. Min Act: -0.0001

Data Index: 1007368 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1288564 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1871. Min Act: -0.0001

Data Index: 595622 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1918. Min Act: -0.0001

Data Index: 6235 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2018. Min Act: -0.0001

Data Index: 750380 (C4 (Web Text))

Max Activating Token Index: 435