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

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

Neuron 274 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.1808. Min Act: -0.1700

Data Index: 1300317 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.1495. Min Act: -0.1700

Data Index: 230968 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.2433. Min Act: -0.1700

Data Index: 394910 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.1183. Min Act: -0.1700

Data Index: 260779 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.1495. Min Act: -0.1700

Data Index: 206775 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.1495. Min Act: -0.1700

Data Index: 320379 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.1495. Min Act: -0.1700

Data Index: 454800 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.1183. Min Act: -0.1700

Data Index: 1206550 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.0870. Min Act: -0.1700

Data Index: 1133172 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.1183. Min Act: -0.1700

Data Index: 147885 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.1183. Min Act: -0.1700

Data Index: 1286483 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.0870. Min Act: -0.1700

Data Index: 551456 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.0870. Min Act: -0.1700

Data Index: 577485 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.0558. Min Act: -0.1700

Data Index: 1049387 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.0558. Min Act: -0.1700

Data Index: 851432 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.0558. Min Act: -0.1700

Data Index: 800915 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.1183. Min Act: -0.1700

Data Index: 1063835 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.0558. Min Act: -0.1700

Data Index: 641767 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.0245. Min Act: -0.1700

Data Index: 408493 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 5.2433. Min Range: -5.2433

Max Act: 5.0870. Min Act: -0.1700

Data Index: 1043468 (C4 (Web Text))

Max Activating Token Index: 494