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

Dataset: Open Web Text

Neuron 651 in Layer 0

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: 1.2393. Min Range: -1.2393

Max Act: 1.2393. Min Act: -0.1022

Data Index: 1976794 (Open Web Text)

Max Activating Token Index: 392

Text #1

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.2389. Min Act: -0.1056

Data Index: 261264 (Open Web Text)

Max Activating Token Index: 635

Text #2

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.2173. Min Act: -0.0628

Data Index: 7318618 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.2079. Min Act: -0.0646

Data Index: 5548857 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.2074. Min Act: -0.1512

Data Index: 3825822 (Open Web Text)

Max Activating Token Index: 470

Text #5

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1915. Min Act: -0.1093

Data Index: 4705379 (Open Web Text)

Max Activating Token Index: 483

Text #6

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1847. Min Act: -0.1074

Data Index: 2854893 (Open Web Text)

Max Activating Token Index: 885

Text #7

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1846. Min Act: -0.0915

Data Index: 3709502 (Open Web Text)

Max Activating Token Index: 471

Text #8

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1880. Min Act: -0.0822

Data Index: 1169403 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1736. Min Act: -0.0965

Data Index: 7005504 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1679. Min Act: -0.0516

Data Index: 4499770 (Open Web Text)

Max Activating Token Index: 238

Text #11

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1737. Min Act: -0.1377

Data Index: 2327260 (Open Web Text)

Max Activating Token Index: 337

Text #12

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1673. Min Act: -0.0717

Data Index: 4326722 (Open Web Text)

Max Activating Token Index: 917

Text #13

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1631. Min Act: -0.0941

Data Index: 3502349 (Open Web Text)

Max Activating Token Index: 296

Text #14

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1571. Min Act: -0.1286

Data Index: 5852658 (Open Web Text)

Max Activating Token Index: 858

Text #15

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1605. Min Act: -0.1066

Data Index: 4892914 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1500. Min Act: -0.1148

Data Index: 7301054 (Open Web Text)

Max Activating Token Index: 302

Text #17

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1509. Min Act: -0.1276

Data Index: 3101876 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1522. Min Act: -0.1185

Data Index: 1230286 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.2393. Min Range: -1.2393

Max Act: 1.1556. Min Act: -0.0446

Data Index: 188617 (Open Web Text)

Max Activating Token Index: 11