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

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

Neuron 1839 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: 3.6184. Min Range: -3.6184

Max Act: 3.6184. Min Act: -0.1695

Data Index: 1641436 (Python Code)

Max Activating Token Index: 534

Text #1

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.6125. Min Act: -0.1700

Data Index: 1444312 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.3500. Min Act: -0.1678

Data Index: 1503235 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.2231. Min Act: -0.1699

Data Index: 1360216 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.2329. Min Act: -0.1700

Data Index: 1563957 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.2139. Min Act: -0.1700

Data Index: 1472210 (Python Code)

Max Activating Token Index: 395

Text #6

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.1938. Min Act: -0.1700

Data Index: 638447 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.1759. Min Act: -0.1699

Data Index: 1418572 (Python Code)

Max Activating Token Index: 337

Text #8

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.1962. Min Act: -0.1700

Data Index: 1619545 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.1674. Min Act: -0.1690

Data Index: 984439 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.1504. Min Act: -0.1700

Data Index: 1629410 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.1713. Min Act: -0.1697

Data Index: 188949 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.1363. Min Act: -0.1700

Data Index: 1600675 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.1270. Min Act: -0.1700

Data Index: 1431867 (Python Code)

Max Activating Token Index: 474

Text #14

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.1380. Min Act: -0.1700

Data Index: 1110294 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.0831. Min Act: -0.1700

Data Index: 1589893 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1618587 (Python Code)

Max Activating Token Index: 610

Text #17

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.1062. Min Act: -0.1647

Data Index: 328154 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.0531. Min Act: -0.1700

Data Index: 1374333 (Python Code)

Max Activating Token Index: 964

Text #19

Max Range: 3.6184. Min Range: -3.6184

Max Act: 3.0636. Min Act: -0.1700

Data Index: 1591568 (Python Code)

Max Activating Token Index: 335