Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2797 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.4448. Min Act: -0.1644

Data Index: 7382367 (Open Web Text)

Max Activating Token Index: 141

Text #1

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.4165. Min Act: -0.1692

Data Index: 5095618 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.4130. Min Act: -0.1689

Data Index: 3477762 (Open Web Text)

Max Activating Token Index: 488

Text #3

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.4022. Min Act: -0.1473

Data Index: 4234379 (Open Web Text)

Max Activating Token Index: 155

Text #4

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.4031. Min Act: -0.1700

Data Index: 5209228 (Open Web Text)

Max Activating Token Index: 370

Text #5

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3821. Min Act: -0.1546

Data Index: 7191525 (Open Web Text)

Max Activating Token Index: 826

Text #6

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3828. Min Act: -0.1691

Data Index: 5657926 (Open Web Text)

Max Activating Token Index: 485

Text #7

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3716. Min Act: -0.1700

Data Index: 1776698 (Open Web Text)

Max Activating Token Index: 145

Text #8

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3825. Min Act: -0.1691

Data Index: 7191515 (Open Web Text)

Max Activating Token Index: 401

Text #9

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3709. Min Act: -0.1700

Data Index: 6428380 (Open Web Text)

Max Activating Token Index: 520

Text #10

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3586. Min Act: -0.1502

Data Index: 261032 (Open Web Text)

Max Activating Token Index: 463

Text #11

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3561. Min Act: -0.1691

Data Index: 7045985 (Open Web Text)

Max Activating Token Index: 241

Text #12

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3535. Min Act: -0.1630

Data Index: 2912682 (Open Web Text)

Max Activating Token Index: 738

Text #13

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3579. Min Act: -0.1693

Data Index: 4050209 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3538. Min Act: -0.1691

Data Index: 6313305 (Open Web Text)

Max Activating Token Index: 821

Text #15

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3577. Min Act: -0.1691

Data Index: 4207350 (Open Web Text)

Max Activating Token Index: 647

Text #16

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3494. Min Act: -0.1542

Data Index: 3286631 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3513. Min Act: -0.1699

Data Index: 5128463 (Open Web Text)

Max Activating Token Index: 249

Text #18

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3481. Min Act: -0.1451

Data Index: 2278779 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 1.4448. Min Range: -1.4448

Max Act: 1.3539. Min Act: -0.1700

Data Index: 5657910 (Open Web Text)

Max Activating Token Index: 361