Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 415 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.6212. Min Act: -0.1699

Data Index: 1470430 (Python Code)

Max Activating Token Index: 276

Text #1

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.2892. Min Act: -0.1693

Data Index: 1416246 (Python Code)

Max Activating Token Index: 851

Text #2

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.2394. Min Act: -0.1699

Data Index: 1524986 (Python Code)

Max Activating Token Index: 577

Text #3

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.2295. Min Act: -0.1700

Data Index: 1579454 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.2016. Min Act: -0.1698

Data Index: 1377677 (Python Code)

Max Activating Token Index: 611

Text #5

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1847. Min Act: -0.1699

Data Index: 1420256 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1769. Min Act: -0.1698

Data Index: 1580070 (Python Code)

Max Activating Token Index: 979

Text #7

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1691. Min Act: -0.1698

Data Index: 1599785 (Python Code)

Max Activating Token Index: 553

Text #8

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1697. Min Act: -0.1700

Data Index: 1633982 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1530. Min Act: -0.1698

Data Index: 1608190 (Python Code)

Max Activating Token Index: 960

Text #10

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1375. Min Act: -0.1700

Data Index: 1517965 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1500. Min Act: -0.1700

Data Index: 1514846 (Python Code)

Max Activating Token Index: 762

Text #12

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1502. Min Act: -0.1700

Data Index: 1556591 (Python Code)

Max Activating Token Index: 582

Text #13

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1342. Min Act: -0.1700

Data Index: 1556429 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1435. Min Act: -0.1699

Data Index: 1524615 (Python Code)

Max Activating Token Index: 982

Text #15

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1318. Min Act: -0.1700

Data Index: 1451743 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1255. Min Act: -0.1700

Data Index: 1400827 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1201. Min Act: -0.1698

Data Index: 1387204 (Python Code)

Max Activating Token Index: 654

Text #18

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1296. Min Act: -0.1690

Data Index: 1650370 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 3.6212. Min Range: -3.6212

Max Act: 3.1222. Min Act: -0.1700

Data Index: 1633984 (Python Code)

Max Activating Token Index: 486