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

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

Neuron 3801 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1007277 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3620. Min Act: -0.0001

Data Index: 622296 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.3183. Min Act: -0.0001

Data Index: 569208 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2843. Min Act: -0.0001

Data Index: 1046157 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2267. Min Act: -0.0001

Data Index: 833319 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2609. Min Act: -0.0001

Data Index: 603965 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2312. Min Act: -0.0001

Data Index: 626325 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2006. Min Act: -0.0001

Data Index: 140431 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1342736 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2028. Min Act: -0.0001

Data Index: 600600 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1988. Min Act: -0.0001

Data Index: 58735 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2055. Min Act: -0.0001

Data Index: 757242 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1254840 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1977. Min Act: -0.0001

Data Index: 285732 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2237. Min Act: -0.0001

Data Index: 1130216 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1932. Min Act: -0.0001

Data Index: 665575 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1979. Min Act: -0.0001

Data Index: 798004 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1821. Min Act: -0.0001

Data Index: 293298 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.2063. Min Act: -0.0001

Data Index: 837763 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.3620. Min Range: -0.3620

Max Act: 0.1907. Min Act: -0.0001

Data Index: 1214528 (C4 (Web Text))

Max Activating Token Index: 603