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

Dataset: Open Web Text

Neuron 2408 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: 2.1357. Min Range: -2.1357

Max Act: 2.1357. Min Act: -0.1700

Data Index: 541921 (Open Web Text)

Max Activating Token Index: 708

Text #1

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.1030. Min Act: -0.1700

Data Index: 5751737 (Open Web Text)

Max Activating Token Index: 934

Text #2

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0926. Min Act: -0.1700

Data Index: 4726839 (Open Web Text)

Max Activating Token Index: 405

Text #3

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0895. Min Act: -0.1700

Data Index: 8143976 (Open Web Text)

Max Activating Token Index: 832

Text #4

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0995. Min Act: -0.1700

Data Index: 2188595 (Open Web Text)

Max Activating Token Index: 929

Text #5

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0932. Min Act: -0.1700

Data Index: 5085306 (Open Web Text)

Max Activating Token Index: 99

Text #6

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0662. Min Act: -0.1700

Data Index: 6152304 (Open Web Text)

Max Activating Token Index: 795

Text #7

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0721. Min Act: -0.1700

Data Index: 4066287 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0661. Min Act: -0.1700

Data Index: 5365187 (Open Web Text)

Max Activating Token Index: 165

Text #9

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0657. Min Act: -0.1700

Data Index: 5135795 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0832. Min Act: -0.1700

Data Index: 4155664 (Open Web Text)

Max Activating Token Index: 900

Text #11

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0767. Min Act: -0.1700

Data Index: 6132162 (Open Web Text)

Max Activating Token Index: 544

Text #12

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0607. Min Act: -0.1700

Data Index: 1659432 (Open Web Text)

Max Activating Token Index: 617

Text #13

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0533. Min Act: -0.1700

Data Index: 3194988 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0614. Min Act: -0.1700

Data Index: 2499945 (Open Web Text)

Max Activating Token Index: 457

Text #15

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0646. Min Act: -0.1700

Data Index: 4893463 (Open Web Text)

Max Activating Token Index: 321

Text #16

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0416. Min Act: -0.1700

Data Index: 871038 (Open Web Text)

Max Activating Token Index: 919

Text #17

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0564. Min Act: -0.1700

Data Index: 8049969 (Open Web Text)

Max Activating Token Index: 523

Text #18

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0486. Min Act: -0.1700

Data Index: 2052024 (Open Web Text)

Max Activating Token Index: 153

Text #19

Max Range: 2.1357. Min Range: -2.1357

Max Act: 2.0383. Min Act: -0.1700

Data Index: 1621579 (Open Web Text)

Max Activating Token Index: 90