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

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

Neuron 2010 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: 0.1941. Min Range: -0.1941

Max Act: 0.1941. Min Act: -0.0001

Data Index: 477697 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1789. Min Act: -0.0000

Data Index: 122267 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1354931 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1346. Min Act: -0.0000

Data Index: 376601 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1291819 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1435. Min Act: -0.0000

Data Index: 724091 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1196. Min Act: -0.0000

Data Index: 48830 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1346001 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1241. Min Act: -0.0000

Data Index: 428247 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1188. Min Act: -0.0000

Data Index: 983923 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1129. Min Act: -0.0000

Data Index: 72916 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1235890 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1143. Min Act: -0.0000

Data Index: 519764 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1119. Min Act: -0.0000

Data Index: 223296 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1197. Min Act: -0.0000

Data Index: 989531 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1019528 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1170032 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1096. Min Act: -0.0000

Data Index: 292866 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1080. Min Act: -0.0000

Data Index: 300953 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1075. Min Act: -0.0000

Data Index: 693793 (C4 (Web Text))

Max Activating Token Index: 65