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

Dataset: Open Web Text

Neuron 2136 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: 3.0454. Min Range: -3.0454

Max Act: 3.0454. Min Act: -0.1700

Data Index: 8411729 (Open Web Text)

Max Activating Token Index: 572

Text #1

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9830. Min Act: -0.1700

Data Index: 1164569 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9887. Min Act: -0.1700

Data Index: 6152409 (Open Web Text)

Max Activating Token Index: 687

Text #3

Max Range: 3.0454. Min Range: -3.0454

Max Act: 3.0017. Min Act: -0.1700

Data Index: 94000 (Open Web Text)

Max Activating Token Index: 38

Text #4

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9889. Min Act: -0.1700

Data Index: 5025083 (Open Web Text)

Max Activating Token Index: 564

Text #5

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9524. Min Act: -0.1700

Data Index: 2714944 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9890. Min Act: -0.1700

Data Index: 1404152 (Open Web Text)

Max Activating Token Index: 614

Text #7

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9744. Min Act: -0.1700

Data Index: 733796 (Open Web Text)

Max Activating Token Index: 419

Text #8

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9663. Min Act: -0.1700

Data Index: 6337833 (Open Web Text)

Max Activating Token Index: 776

Text #9

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9554. Min Act: -0.1700

Data Index: 6586264 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9527. Min Act: -0.1700

Data Index: 802008 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9557. Min Act: -0.1700

Data Index: 7835246 (Open Web Text)

Max Activating Token Index: 519

Text #12

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9495. Min Act: -0.1700

Data Index: 432281 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9374. Min Act: -0.1700

Data Index: 3744000 (Open Web Text)

Max Activating Token Index: 301

Text #14

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9496. Min Act: -0.1700

Data Index: 3989318 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9319. Min Act: -0.1700

Data Index: 5909251 (Open Web Text)

Max Activating Token Index: 193

Text #16

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9063. Min Act: -0.1700

Data Index: 6244247 (Open Web Text)

Max Activating Token Index: 1003

Text #17

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9204. Min Act: -0.1700

Data Index: 3062692 (Open Web Text)

Max Activating Token Index: 420

Text #18

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9085. Min Act: -0.1700

Data Index: 7508262 (Open Web Text)

Max Activating Token Index: 502

Text #19

Max Range: 3.0454. Min Range: -3.0454

Max Act: 2.9116. Min Act: -0.1700

Data Index: 369170 (Open Web Text)

Max Activating Token Index: 564