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

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

Neuron 3788 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1463500 (Python Code)

Max Activating Token Index: 1018

Text #1

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1415350 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1700. Min Act: -0.0000

Data Index: 918811 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1124105 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1390. Min Act: -0.0000

Data Index: 547342 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1516289 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1542386 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1419. Min Act: -0.0000

Data Index: 786410 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1083331 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1119737 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1183680 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1005144 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1375. Min Act: -0.0000

Data Index: 135072 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1256. Min Act: -0.0000

Data Index: 338587 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1330. Min Act: -0.0000

Data Index: 460695 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1644256 (Python Code)

Max Activating Token Index: 581

Text #16

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1084443 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1569683 (Python Code)

Max Activating Token Index: 500

Text #18

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1385408 (Python Code)

Max Activating Token Index: 896

Text #19

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1427493 (Python Code)

Max Activating Token Index: 507