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

Dataset: Open Web Text

Neuron 252 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: 4.1338. Min Range: -4.1338

Max Act: 4.1018. Min Act: -0.1700

Data Index: 2523504 (Open Web Text)

Max Activating Token Index: 530

Text #1

Max Range: 4.1338. Min Range: -4.1338

Max Act: 4.1338. Min Act: -0.1700

Data Index: 4231106 (Open Web Text)

Max Activating Token Index: 404

Text #2

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.9269. Min Act: -0.1700

Data Index: 720585 (Open Web Text)

Max Activating Token Index: 275

Text #3

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.8000. Min Act: -0.1700

Data Index: 3626172 (Open Web Text)

Max Activating Token Index: 935

Text #4

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.7999. Min Act: -0.1700

Data Index: 1922393 (Open Web Text)

Max Activating Token Index: 658

Text #5

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.7788. Min Act: -0.1700

Data Index: 1302634 (Open Web Text)

Max Activating Token Index: 595

Text #6

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.7840. Min Act: -0.1700

Data Index: 8104251 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.7395. Min Act: -0.1700

Data Index: 7584652 (Open Web Text)

Max Activating Token Index: 560

Text #8

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6893. Min Act: -0.1700

Data Index: 8504336 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.7131. Min Act: -0.1700

Data Index: 658317 (Open Web Text)

Max Activating Token Index: 851

Text #10

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6787. Min Act: -0.1700

Data Index: 1983467 (Open Web Text)

Max Activating Token Index: 797

Text #11

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6735. Min Act: -0.1700

Data Index: 3891946 (Open Web Text)

Max Activating Token Index: 707

Text #12

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6694. Min Act: -0.1700

Data Index: 704381 (Open Web Text)

Max Activating Token Index: 318

Text #13

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6490. Min Act: -0.1700

Data Index: 1041679 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6658. Min Act: -0.1700

Data Index: 3601260 (Open Web Text)

Max Activating Token Index: 618

Text #15

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6176. Min Act: -0.1700

Data Index: 4970841 (Open Web Text)

Max Activating Token Index: 170

Text #16

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6574. Min Act: -0.1700

Data Index: 2002147 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6645. Min Act: -0.1700

Data Index: 2478453 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6554. Min Act: -0.1700

Data Index: 4662769 (Open Web Text)

Max Activating Token Index: 911

Text #19

Max Range: 4.1338. Min Range: -4.1338

Max Act: 3.6480. Min Act: -0.1700

Data Index: 1817179 (Open Web Text)

Max Activating Token Index: 710