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

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

Neuron 2836 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: 0.1704. Min Range: -0.1704

Max Act: 0.1704. Min Act: -0.0001

Data Index: 1620024 (Python Code)

Max Activating Token Index: 186

Text #1

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1524378 (Python Code)

Max Activating Token Index: 861

Text #2

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1525. Min Act: -0.0001

Data Index: 297110 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1609144 (Python Code)

Max Activating Token Index: 150

Text #4

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1569184 (Python Code)

Max Activating Token Index: 659

Text #5

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1000019 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1653992 (Python Code)

Max Activating Token Index: 871

Text #7

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1594096 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1333. Min Act: -0.0001

Data Index: 830425 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1399236 (Python Code)

Max Activating Token Index: 450

Text #10

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1442012 (Python Code)

Max Activating Token Index: 359

Text #11

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1580789 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1496142 (Python Code)

Max Activating Token Index: 671

Text #13

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1226. Min Act: -0.0001

Data Index: 248934 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1574008 (Python Code)

Max Activating Token Index: 827

Text #15

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1232. Min Act: -0.0001

Data Index: 953109 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1392045 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1254. Min Act: -0.0001

Data Index: 996567 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1637412 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1404189 (Python Code)

Max Activating Token Index: 496