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

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

Neuron 324 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: 4.4176. Min Range: -4.4176

Max Act: 4.4176. Min Act: -0.1347

Data Index: 394963 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.4133. Min Act: -0.1683

Data Index: 822458 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.2130. Min Act: -0.1700

Data Index: 1126050 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1897. Min Act: -0.1691

Data Index: 743014 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1814. Min Act: -0.1700

Data Index: 1014213 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1759. Min Act: -0.1694

Data Index: 1269995 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1641. Min Act: -0.1693

Data Index: 733246 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1559. Min Act: -0.1688

Data Index: 184980 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1780. Min Act: -0.1698

Data Index: 282737 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1466. Min Act: -0.1695

Data Index: 1112638 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1336. Min Act: -0.1699

Data Index: 438484 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1656. Min Act: -0.1696

Data Index: 254686 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1531. Min Act: -0.1655

Data Index: 498635 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1216. Min Act: -0.1700

Data Index: 129571 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1236. Min Act: -0.1700

Data Index: 319382 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1074. Min Act: -0.1700

Data Index: 215020 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.0947. Min Act: -0.1700

Data Index: 262849 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1089. Min Act: -0.1404

Data Index: 818560 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.1097. Min Act: -0.1699

Data Index: 802189 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 4.4176. Min Range: -4.4176

Max Act: 4.0941. Min Act: -0.1681

Data Index: 761392 (C4 (Web Text))

Max Activating Token Index: 355