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

Dataset: Open Web Text

Neuron 1631 in Layer 1

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: 4.3306. Min Range: -4.3306

Max Act: 4.3190. Min Act: -0.1700

Data Index: 2234954 (Open Web Text)

Max Activating Token Index: 994

Text #1

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.3306. Min Act: -0.1700

Data Index: 2543770 (Open Web Text)

Max Activating Token Index: 289

Text #2

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2787. Min Act: -0.1700

Data Index: 7892458 (Open Web Text)

Max Activating Token Index: 183

Text #3

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2754. Min Act: -0.1700

Data Index: 3793600 (Open Web Text)

Max Activating Token Index: 127

Text #4

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2796. Min Act: -0.1700

Data Index: 5894234 (Open Web Text)

Max Activating Token Index: 848

Text #5

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2695. Min Act: -0.1700

Data Index: 1592040 (Open Web Text)

Max Activating Token Index: 557

Text #6

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2763. Min Act: -0.1700

Data Index: 775852 (Open Web Text)

Max Activating Token Index: 191

Text #7

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2547. Min Act: -0.1700

Data Index: 7488558 (Open Web Text)

Max Activating Token Index: 848

Text #8

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2550. Min Act: -0.1700

Data Index: 5688259 (Open Web Text)

Max Activating Token Index: 588

Text #9

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2863. Min Act: -0.1700

Data Index: 3136434 (Open Web Text)

Max Activating Token Index: 268

Text #10

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2585. Min Act: -0.1700

Data Index: 3092940 (Open Web Text)

Max Activating Token Index: 755

Text #11

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2533. Min Act: -0.1700

Data Index: 830465 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2801. Min Act: -0.1700

Data Index: 55730 (Open Web Text)

Max Activating Token Index: 121

Text #13

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2494. Min Act: -0.1700

Data Index: 1769427 (Open Web Text)

Max Activating Token Index: 211

Text #14

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2705. Min Act: -0.1700

Data Index: 5630681 (Open Web Text)

Max Activating Token Index: 779

Text #15

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2706. Min Act: -0.1700

Data Index: 746732 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2460. Min Act: -0.1700

Data Index: 5369787 (Open Web Text)

Max Activating Token Index: 57

Text #17

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2574. Min Act: -0.1700

Data Index: 4306745 (Open Web Text)

Max Activating Token Index: 337

Text #18

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2553. Min Act: -0.1700

Data Index: 3971899 (Open Web Text)

Max Activating Token Index: 219

Text #19

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2455. Min Act: -0.1700

Data Index: 3432227 (Open Web Text)

Max Activating Token Index: 204