Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 630 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.3182. Min Act: -0.0000

Data Index: 638087 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1367931 (Python Code)

Max Activating Token Index: 935

Text #2

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.2908. Min Act: -0.0000

Data Index: 827198 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1067140 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.2154. Min Act: -0.0000

Data Index: 337443 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.2109. Min Act: -0.0000

Data Index: 591870 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.2039. Min Act: -0.0000

Data Index: 227854 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1546355 (Python Code)

Max Activating Token Index: 130

Text #8

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.2322. Min Act: -0.0000

Data Index: 366001 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1291090 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1151294 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.1941. Min Act: 0.0000

Data Index: 95749 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.1901. Min Act: -0.0000

Data Index: 614768 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.1768. Min Act: -0.0000

Data Index: 902841 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.1866. Min Act: -0.0000

Data Index: 351678 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.1858. Min Act: -0.0000

Data Index: 680067 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.1792. Min Act: -0.0000

Data Index: 727676 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.1823. Min Act: -0.0000

Data Index: 327543 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1301351 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.3182. Min Range: -0.3182

Max Act: 0.1821. Min Act: -0.0000

Data Index: 250358 (C4 (Web Text))

Max Activating Token Index: 325