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

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

Neuron 1336 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2905. Min Act: -0.0000

Data Index: 313846 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1106202 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1102546 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2448. Min Act: -0.0000

Data Index: 770137 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2376. Min Act: -0.0000

Data Index: 334708 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2262. Min Act: -0.0001

Data Index: 1313216 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2307. Min Act: -0.0000

Data Index: 795936 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2273. Min Act: -0.0000

Data Index: 512751 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2144. Min Act: -0.0001

Data Index: 1094918 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2126. Min Act: -0.0001

Data Index: 503758 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2264. Min Act: -0.0000

Data Index: 990872 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2089. Min Act: -0.0001

Data Index: 398434 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2229. Min Act: -0.0001

Data Index: 781032 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2154. Min Act: -0.0001

Data Index: 832376 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1212780 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2071. Min Act: -0.0000

Data Index: 887437 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1055329 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1184135 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.1989. Min Act: -0.0001

Data Index: 893896 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.2905. Min Range: -0.2905

Max Act: 0.1914. Min Act: -0.0001

Data Index: 164789 (C4 (Web Text))

Max Activating Token Index: 666