Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1452 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.4401. Min Act: -0.1700

Data Index: 1217434 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.4558. Min Act: -0.1700

Data Index: 443786 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.4245. Min Act: -0.1700

Data Index: 328222 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.4401. Min Act: -0.1700

Data Index: 1295621 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.4088. Min Act: -0.1700

Data Index: 579347 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.3774. Min Act: -0.1700

Data Index: 219288 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.3774. Min Act: -0.1700

Data Index: 1331829 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.3617. Min Act: -0.1700

Data Index: 1323500 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.3617. Min Act: -0.1700

Data Index: 650841 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.3146. Min Act: -0.1700

Data Index: 966390 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.2989. Min Act: -0.1700

Data Index: 1233317 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.2832. Min Act: -0.1700

Data Index: 1131001 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.3146. Min Act: -0.1700

Data Index: 1231380 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.2361. Min Act: -0.1700

Data Index: 1193291 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.2675. Min Act: -0.1700

Data Index: 1004209 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.2675. Min Act: -0.1700

Data Index: 552470 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.2518. Min Act: -0.1700

Data Index: 348351 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.2361. Min Act: -0.1700

Data Index: 566578 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.2361. Min Act: -0.1700

Data Index: 1114337 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 3.4558. Min Range: -3.4558

Max Act: 3.2361. Min Act: -0.1700

Data Index: 1308196 (C4 (Web Text))

Max Activating Token Index: 504