Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2232 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1269. Min Act: -0.0001

Data Index: 473117 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1208574 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1191170 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1209. Min Act: -0.0001

Data Index: 624344 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1170688 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1138. Min Act: -0.0001

Data Index: 144619 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0954. Min Act: -0.0001

Data Index: 321346 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0985. Min Act: -0.0001

Data Index: 267497 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0932. Min Act: -0.0001

Data Index: 1156899 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1239122 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1192138 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0910. Min Act: -0.0001

Data Index: 42658 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1120873 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1332825 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1039943 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0846. Min Act: -0.0001

Data Index: 437404 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0765. Min Act: -0.0001

Data Index: 274104 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1088425 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0866. Min Act: -0.0001

Data Index: 73337 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0872. Min Act: -0.0001

Data Index: 938296 (C4 (Web Text))

Max Activating Token Index: 836