Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5401 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1499111 (Python Code)

Max Activating Token Index: 376

Text #1

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1520712 (Python Code)

Max Activating Token Index: 167

Text #2

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1210220 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1333. Min Act: -0.0001

Data Index: 1577716 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1635816 (Python Code)

Max Activating Token Index: 924

Text #5

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1505028 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1270. Min Act: -0.0001

Data Index: 889964 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1337865 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1561767 (Python Code)

Max Activating Token Index: 581

Text #9

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1626031 (Python Code)

Max Activating Token Index: 393

Text #10

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1434471 (Python Code)

Max Activating Token Index: 908

Text #11

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1108. Min Act: -0.0001

Data Index: 814548 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1105272 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1528475 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1016. Min Act: -0.0001

Data Index: 501240 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1600742 (Python Code)

Max Activating Token Index: 870

Text #16

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1031. Min Act: -0.0001

Data Index: 481619 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1025273 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1050. Min Act: -0.0001

Data Index: 789274 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1559977 (Python Code)

Max Activating Token Index: 446