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

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

Neuron 284 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: 8.6324. Min Range: -8.6324

Max Act: 8.5795. Min Act: -0.1699

Data Index: 1029670 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 8.6324. Min Range: -8.6324

Max Act: 8.6324. Min Act: -0.1699

Data Index: 1030419 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 8.6324. Min Range: -8.6324

Max Act: 8.4045. Min Act: -0.1695

Data Index: 1255791 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 8.6324. Min Range: -8.6324

Max Act: 8.3201. Min Act: -0.1700

Data Index: 146745 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 8.6324. Min Range: -8.6324

Max Act: 8.2078. Min Act: -0.1700

Data Index: 1043368 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 8.6324. Min Range: -8.6324

Max Act: 8.0012. Min Act: -0.1699

Data Index: 580840 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.9802. Min Act: -0.1700

Data Index: 181778 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.8272. Min Act: -0.1700

Data Index: 610636 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.8467. Min Act: -0.1700

Data Index: 315241 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.9157. Min Act: -0.1700

Data Index: 893432 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.9185. Min Act: -0.1699

Data Index: 941441 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.8633. Min Act: -0.1693

Data Index: 1085318 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.9064. Min Act: -0.1700

Data Index: 845228 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.8878. Min Act: -0.1696

Data Index: 147505 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.7484. Min Act: -0.1700

Data Index: 614694 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.6545. Min Act: -0.1694

Data Index: 81205 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.7164. Min Act: -0.1700

Data Index: 62818 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.6882. Min Act: -0.1700

Data Index: 989427 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.5824. Min Act: -0.1700

Data Index: 1019578 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 8.6324. Min Range: -8.6324

Max Act: 7.6127. Min Act: -0.1699

Data Index: 1022034 (C4 (Web Text))

Max Activating Token Index: 883