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

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

Neuron 1881 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: 0.1565. Min Range: -0.1565

Max Act: 0.1565. Min Act: -0.0001

Data Index: 331869 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1236130 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1079649 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1422. Min Act: -0.0001

Data Index: 248281 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1296. Min Act: -0.0001

Data Index: 549124 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1321. Min Act: -0.0001

Data Index: 395525 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1233. Min Act: -0.0001

Data Index: 198606 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1200. Min Act: -0.0001

Data Index: 967064 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1249. Min Act: -0.0001

Data Index: 663286 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1251. Min Act: -0.0001

Data Index: 616767 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1609805 (Python Code)

Max Activating Token Index: 564

Text #11

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1065732 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1166. Min Act: -0.0001

Data Index: 716266 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1246. Min Act: -0.0001

Data Index: 834772 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1155. Min Act: -0.0001

Data Index: 370235 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1111. Min Act: -0.0001

Data Index: 72688 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1419724 (Python Code)

Max Activating Token Index: 720

Text #17

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1169. Min Act: -0.0001

Data Index: 34166 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1045. Min Act: -0.0001

Data Index: 942910 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1433228 (Python Code)

Max Activating Token Index: 734