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

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

Neuron 409 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: 5.0048. Min Range: -5.0048

Max Act: 5.0048. Min Act: -0.1700

Data Index: 432139 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.3906. Min Act: -0.1670

Data Index: 990298 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.4042. Min Act: -0.1699

Data Index: 39303 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.3350. Min Act: 0.2813

Data Index: 367238 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.2264. Min Act: -0.1699

Data Index: 1240635 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.2185. Min Act: -0.1696

Data Index: 1329384 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.2249. Min Act: -0.1699

Data Index: 532303 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.2253. Min Act: -0.1449

Data Index: 1188261 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.2199. Min Act: -0.1509

Data Index: 1198161 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.2039. Min Act: 0.2789

Data Index: 88805 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.1630. Min Act: -0.1102

Data Index: 22132 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.1469. Min Act: -0.0642

Data Index: 220179 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.1320. Min Act: -0.1314

Data Index: 686202 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.1265. Min Act: -0.0885

Data Index: 924771 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.0950. Min Act: -0.1699

Data Index: 348604 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.1078. Min Act: -0.1699

Data Index: 98650 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.0863. Min Act: -0.1692

Data Index: 37799 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.0829. Min Act: -0.0456

Data Index: 493355 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.0754. Min Act: -0.1308

Data Index: 626815 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.0548. Min Act: -0.1689

Data Index: 1233155 (C4 (Web Text))

Max Activating Token Index: 156