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

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

Neuron 3108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2516. Min Act: -0.0001

Data Index: 1336066 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2460. Min Act: -0.0001

Data Index: 831697 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1222334 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1301092 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1013419 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1989. Min Act: -0.0001

Data Index: 586549 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2106. Min Act: -0.0001

Data Index: 1196240 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1067616 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1954. Min Act: -0.0001

Data Index: 105512 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2088. Min Act: -0.0001

Data Index: 94642 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2158. Min Act: -0.0001

Data Index: 237442 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2073. Min Act: -0.0001

Data Index: 557809 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1138591 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1179391 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1922. Min Act: -0.0000

Data Index: 204965 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1987. Min Act: -0.0000

Data Index: 927214 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1986. Min Act: -0.0001

Data Index: 898435 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1994. Min Act: -0.0001

Data Index: 331324 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1819. Min Act: -0.0000

Data Index: 69016 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1855. Min Act: -0.0000

Data Index: 658677 (C4 (Web Text))

Max Activating Token Index: 687