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

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

Neuron 1672 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: 5.4436. Min Range: -5.4436

Max Act: 5.4436. Min Act: -0.1700

Data Index: 614153 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.4436. Min Act: -0.1700

Data Index: 1017023 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.2561. Min Act: -0.1700

Data Index: 1209668 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.2874. Min Act: -0.1700

Data Index: 1346624 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.1936. Min Act: -0.1698

Data Index: 282374 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.1311. Min Act: -0.1700

Data Index: 432660 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.1311. Min Act: -0.1700

Data Index: 921355 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.0999. Min Act: -0.1700

Data Index: 1295794 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.0999. Min Act: -0.1700

Data Index: 1389893 (Python Code)

Max Activating Token Index: 359

Text #9

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.0999. Min Act: -0.1700

Data Index: 1276224 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.0686. Min Act: -0.1700

Data Index: 1356402 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.0374. Min Act: -0.1700

Data Index: 595770 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.0061. Min Act: -0.1700

Data Index: 485682 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 5.4436. Min Range: -5.4436

Max Act: 4.9749. Min Act: -0.1700

Data Index: 520208 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 5.4436. Min Range: -5.4436

Max Act: 5.0061. Min Act: -0.1700

Data Index: 751374 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 5.4436. Min Range: -5.4436

Max Act: 4.9749. Min Act: -0.1700

Data Index: 258270 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 5.4436. Min Range: -5.4436

Max Act: 4.9749. Min Act: -0.1700

Data Index: 55298 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 5.4436. Min Range: -5.4436

Max Act: 4.9749. Min Act: -0.1700

Data Index: 518075 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 5.4436. Min Range: -5.4436

Max Act: 4.9749. Min Act: -0.1700

Data Index: 740188 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 5.4436. Min Range: -5.4436

Max Act: 4.9436. Min Act: -0.1700

Data Index: 676206 (C4 (Web Text))

Max Activating Token Index: 347