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

Dataset: Open Web Text

Neuron 2538 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: 1.6804. Min Range: -1.6804

Max Act: 1.6804. Min Act: -0.1700

Data Index: 1025371 (Open Web Text)

Max Activating Token Index: 813

Text #1

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.6033. Min Act: -0.1700

Data Index: 6688479 (Open Web Text)

Max Activating Token Index: 753

Text #2

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.6005. Min Act: -0.1700

Data Index: 6146696 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5642. Min Act: -0.1700

Data Index: 7441180 (Open Web Text)

Max Activating Token Index: 451

Text #4

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5721. Min Act: -0.1700

Data Index: 4801590 (Open Web Text)

Max Activating Token Index: 861

Text #5

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5737. Min Act: -0.1700

Data Index: 7823297 (Open Web Text)

Max Activating Token Index: 294

Text #6

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5596. Min Act: -0.1699

Data Index: 3118188 (Open Web Text)

Max Activating Token Index: 91

Text #7

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5516. Min Act: -0.1699

Data Index: 6195302 (Open Web Text)

Max Activating Token Index: 600

Text #8

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5468. Min Act: -0.1700

Data Index: 2433666 (Open Web Text)

Max Activating Token Index: 441

Text #9

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5469. Min Act: -0.1700

Data Index: 5607612 (Open Web Text)

Max Activating Token Index: 714

Text #10

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5424. Min Act: -0.1699

Data Index: 319339 (Open Web Text)

Max Activating Token Index: 170

Text #11

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5403. Min Act: -0.1700

Data Index: 1819962 (Open Web Text)

Max Activating Token Index: 202

Text #12

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5365. Min Act: -0.1700

Data Index: 3587437 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5349. Min Act: -0.1700

Data Index: 2490211 (Open Web Text)

Max Activating Token Index: 454

Text #14

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5164. Min Act: -0.1698

Data Index: 1243950 (Open Web Text)

Max Activating Token Index: 224

Text #15

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5161. Min Act: -0.1700

Data Index: 7275799 (Open Web Text)

Max Activating Token Index: 138

Text #16

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5091. Min Act: -0.1700

Data Index: 3252327 (Open Web Text)

Max Activating Token Index: 421

Text #17

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5181. Min Act: -0.1700

Data Index: 7955148 (Open Web Text)

Max Activating Token Index: 549

Text #18

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5068. Min Act: -0.1700

Data Index: 144739 (Open Web Text)

Max Activating Token Index: 873

Text #19

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5170. Min Act: -0.1699

Data Index: 713036 (Open Web Text)

Max Activating Token Index: 890