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

Dataset: Open Web Text

Neuron 2335 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: 2.1379. Min Range: -2.1379

Max Act: 2.1379. Min Act: -0.1696

Data Index: 1626520 (Open Web Text)

Max Activating Token Index: 485

Text #1

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.1216. Min Act: -0.1696

Data Index: 5849314 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0975. Min Act: -0.1700

Data Index: 1026644 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0969. Min Act: -0.1700

Data Index: 3379939 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0844. Min Act: -0.1700

Data Index: 581775 (Open Web Text)

Max Activating Token Index: 139

Text #5

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0903. Min Act: -0.1700

Data Index: 242262 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0733. Min Act: -0.1700

Data Index: 7488543 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0694. Min Act: -0.1700

Data Index: 3837234 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0634. Min Act: -0.1698

Data Index: 684877 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0613. Min Act: -0.1696

Data Index: 2919289 (Open Web Text)

Max Activating Token Index: 477

Text #10

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0544. Min Act: -0.1698

Data Index: 1316966 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0610. Min Act: -0.1700

Data Index: 453548 (Open Web Text)

Max Activating Token Index: 60

Text #12

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0522. Min Act: -0.1699

Data Index: 2492750 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0465. Min Act: -0.1699

Data Index: 3444685 (Open Web Text)

Max Activating Token Index: 40

Text #14

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0527. Min Act: -0.1696

Data Index: 7786339 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0387. Min Act: -0.1700

Data Index: 2164287 (Open Web Text)

Max Activating Token Index: 88

Text #16

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0413. Min Act: -0.1700

Data Index: 888768 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0396. Min Act: -0.1700

Data Index: 4848913 (Open Web Text)

Max Activating Token Index: 933

Text #18

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0363. Min Act: -0.1696

Data Index: 7980661 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 2.1379. Min Range: -2.1379

Max Act: 2.0346. Min Act: -0.1698

Data Index: 3990051 (Open Web Text)

Max Activating Token Index: 6