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

Dataset: Open Web Text

Neuron 870 in Layer 2

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: 1.8479. Min Range: -1.8479

Max Act: 1.8479. Min Act: -0.1700

Data Index: 7869958 (Open Web Text)

Max Activating Token Index: 581

Text #1

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.8312. Min Act: -0.1699

Data Index: 5610494 (Open Web Text)

Max Activating Token Index: 297

Text #2

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.8111. Min Act: -0.1700

Data Index: 3416716 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.8120. Min Act: -0.1700

Data Index: 6804181 (Open Web Text)

Max Activating Token Index: 686

Text #4

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7965. Min Act: -0.1700

Data Index: 6031399 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7842. Min Act: -0.1700

Data Index: 6304542 (Open Web Text)

Max Activating Token Index: 505

Text #6

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7789. Min Act: -0.1700

Data Index: 5158785 (Open Web Text)

Max Activating Token Index: 359

Text #7

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7656. Min Act: -0.1700

Data Index: 2960237 (Open Web Text)

Max Activating Token Index: 477

Text #8

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7658. Min Act: -0.1700

Data Index: 4481697 (Open Web Text)

Max Activating Token Index: 860

Text #9

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7536. Min Act: -0.1700

Data Index: 3015728 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7494. Min Act: -0.1700

Data Index: 5000262 (Open Web Text)

Max Activating Token Index: 1015

Text #11

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7562. Min Act: -0.1700

Data Index: 76721 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7560. Min Act: -0.1700

Data Index: 1398748 (Open Web Text)

Max Activating Token Index: 147

Text #13

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7619. Min Act: -0.1700

Data Index: 8251224 (Open Web Text)

Max Activating Token Index: 577

Text #14

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7635. Min Act: -0.1700

Data Index: 1660179 (Open Web Text)

Max Activating Token Index: 335

Text #15

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7354. Min Act: -0.1700

Data Index: 5945836 (Open Web Text)

Max Activating Token Index: 180

Text #16

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7544. Min Act: -0.1700

Data Index: 8727665 (Open Web Text)

Max Activating Token Index: 250

Text #17

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7438. Min Act: -0.1700

Data Index: 1157179 (Open Web Text)

Max Activating Token Index: 499

Text #18

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7254. Min Act: -0.1699

Data Index: 618323 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 1.8479. Min Range: -1.8479

Max Act: 1.7184. Min Act: -0.1700

Data Index: 7356908 (Open Web Text)

Max Activating Token Index: 153