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

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

Neuron 605 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: 3.3194. Min Range: -3.3194

Max Act: 3.3194. Min Act: -0.1700

Data Index: 443416 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.2889. Min Act: -0.1554

Data Index: 845651 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.2626. Min Act: -0.1700

Data Index: 1299146 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.2502. Min Act: -0.1700

Data Index: 1105609 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.2165. Min Act: -0.1622

Data Index: 1575221 (Python Code)

Max Activating Token Index: 383

Text #5

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.2155. Min Act: -0.1700

Data Index: 1438870 (Python Code)

Max Activating Token Index: 978

Text #6

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.2077. Min Act: -0.1700

Data Index: 687260 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1923. Min Act: -0.1691

Data Index: 1499811 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1760. Min Act: -0.1700

Data Index: 1291458 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1738. Min Act: -0.1676

Data Index: 1303259 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1559. Min Act: -0.1700

Data Index: 935852 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1482. Min Act: -0.1700

Data Index: 1558774 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1507. Min Act: -0.1700

Data Index: 267019 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1424. Min Act: -0.1700

Data Index: 1504337 (Python Code)

Max Activating Token Index: 261

Text #14

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1381. Min Act: -0.1700

Data Index: 1417625 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1339. Min Act: -0.1700

Data Index: 1584821 (Python Code)

Max Activating Token Index: 468

Text #16

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1341. Min Act: -0.1699

Data Index: 704391 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1158. Min Act: -0.1699

Data Index: 1373010 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.1062. Min Act: -0.1700

Data Index: 962 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 3.3194. Min Range: -3.3194

Max Act: 3.0970. Min Act: -0.1700

Data Index: 1452252 (Python Code)

Max Activating Token Index: 993