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

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

Neuron 2073 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: 1.4138. Min Range: -1.4138

Max Act: 1.3731. Min Act: -0.0001

Data Index: 12081 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.4020. Min Act: -0.0001

Data Index: 801095 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2928. Min Act: -0.0001

Data Index: 537153 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.3250. Min Act: -0.0001

Data Index: 678506 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2726. Min Act: -0.0001

Data Index: 561854 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2172. Min Act: -0.0001

Data Index: 417888 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.4138. Min Act: -0.0001

Data Index: 321063 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2371. Min Act: -0.0000

Data Index: 524550 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1310. Min Act: -0.0001

Data Index: 973087 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2367. Min Act: -0.0001

Data Index: 321124 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2310. Min Act: -0.0001

Data Index: 1211265 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2287. Min Act: -0.0001

Data Index: 129134 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2324. Min Act: -0.0001

Data Index: 1024274 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1861. Min Act: -0.0001

Data Index: 1046589 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1501. Min Act: -0.0001

Data Index: 660567 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1613. Min Act: -0.0001

Data Index: 1318298 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2007. Min Act: -0.0001

Data Index: 340199 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1278. Min Act: -0.0001

Data Index: 1069555 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.1238. Min Act: -0.0001

Data Index: 668331 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.4138. Min Range: -1.4138

Max Act: 1.2238. Min Act: -0.0001

Data Index: 1114870 (C4 (Web Text))

Max Activating Token Index: 263