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

Dataset: Open Web Text

Neuron 2020 in Layer 4

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: 3.0313. Min Range: -3.0313

Max Act: 3.0313. Min Act: -0.1700

Data Index: 7177194 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.7019. Min Act: -0.1700

Data Index: 6461241 (Open Web Text)

Max Activating Token Index: 561

Text #2

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.6921. Min Act: -0.1700

Data Index: 685229 (Open Web Text)

Max Activating Token Index: 458

Text #3

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.6371. Min Act: -0.1700

Data Index: 5279534 (Open Web Text)

Max Activating Token Index: 549

Text #4

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.6098. Min Act: -0.1700

Data Index: 3006585 (Open Web Text)

Max Activating Token Index: 521

Text #5

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.5692. Min Act: -0.1700

Data Index: 6294067 (Open Web Text)

Max Activating Token Index: 597

Text #6

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.5603. Min Act: -0.1700

Data Index: 2105986 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.5369. Min Act: -0.1700

Data Index: 1987445 (Open Web Text)

Max Activating Token Index: 614

Text #8

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.5525. Min Act: -0.1700

Data Index: 5102371 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4877. Min Act: -0.1700

Data Index: 237351 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4906. Min Act: -0.1700

Data Index: 1353121 (Open Web Text)

Max Activating Token Index: 574

Text #11

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4863. Min Act: -0.1700

Data Index: 8150437 (Open Web Text)

Max Activating Token Index: 641

Text #12

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4764. Min Act: -0.1700

Data Index: 7066803 (Open Web Text)

Max Activating Token Index: 552

Text #13

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4468. Min Act: -0.1700

Data Index: 5578491 (Open Web Text)

Max Activating Token Index: 521

Text #14

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4396. Min Act: -0.1700

Data Index: 3901478 (Open Web Text)

Max Activating Token Index: 594

Text #15

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4395. Min Act: -0.1700

Data Index: 1512772 (Open Web Text)

Max Activating Token Index: 539

Text #16

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4246. Min Act: -0.1700

Data Index: 6600718 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4486. Min Act: -0.1700

Data Index: 97047 (Open Web Text)

Max Activating Token Index: 558

Text #18

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4196. Min Act: -0.1700

Data Index: 3285164 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 3.0313. Min Range: -3.0313

Max Act: 2.4125. Min Act: -0.1700

Data Index: 6357082 (Open Web Text)

Max Activating Token Index: 523