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

Dataset: Open Web Text

Neuron 1456 in Layer 5

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: 5.3725. Min Range: -5.3725

Max Act: 5.3267. Min Act: -0.1700

Data Index: 3628221 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.3725. Min Act: -0.1700

Data Index: 5598157 (Open Web Text)

Max Activating Token Index: 1000

Text #2

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2970. Min Act: -0.1700

Data Index: 3204137 (Open Web Text)

Max Activating Token Index: 751

Text #3

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.3051. Min Act: -0.1700

Data Index: 6466879 (Open Web Text)

Max Activating Token Index: 770

Text #4

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2725. Min Act: -0.1700

Data Index: 3969809 (Open Web Text)

Max Activating Token Index: 480

Text #5

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2497. Min Act: -0.1700

Data Index: 6202972 (Open Web Text)

Max Activating Token Index: 580

Text #6

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2523. Min Act: -0.1700

Data Index: 7777116 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2655. Min Act: -0.1700

Data Index: 7321970 (Open Web Text)

Max Activating Token Index: 743

Text #8

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2370. Min Act: -0.1700

Data Index: 5213058 (Open Web Text)

Max Activating Token Index: 871

Text #9

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2455. Min Act: -0.1700

Data Index: 7327562 (Open Web Text)

Max Activating Token Index: 170

Text #10

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2180. Min Act: -0.1700

Data Index: 6968602 (Open Web Text)

Max Activating Token Index: 494

Text #11

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2579. Min Act: -0.1700

Data Index: 302979 (Open Web Text)

Max Activating Token Index: 410

Text #12

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2389. Min Act: -0.1700

Data Index: 7202569 (Open Web Text)

Max Activating Token Index: 660

Text #13

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2299. Min Act: -0.1700

Data Index: 4030231 (Open Web Text)

Max Activating Token Index: 483

Text #14

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2150. Min Act: -0.1700

Data Index: 7066792 (Open Web Text)

Max Activating Token Index: 390

Text #15

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.2131. Min Act: -0.1700

Data Index: 903698 (Open Web Text)

Max Activating Token Index: 1002

Text #16

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.1887. Min Act: -0.1700

Data Index: 4819245 (Open Web Text)

Max Activating Token Index: 301

Text #17

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.1667. Min Act: -0.1700

Data Index: 3681297 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.1981. Min Act: -0.1700

Data Index: 6533782 (Open Web Text)

Max Activating Token Index: 457

Text #19

Max Range: 5.3725. Min Range: -5.3725

Max Act: 5.1578. Min Act: -0.1700

Data Index: 3084383 (Open Web Text)

Max Activating Token Index: 726