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

Dataset: Open Web Text

Neuron 1514 in Layer 6

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: 3.3099. Min Range: -3.3099

Max Act: 3.3099. Min Act: -0.1700

Data Index: 5721639 (Open Web Text)

Max Activating Token Index: 233

Text #1

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.2270. Min Act: -0.1700

Data Index: 2216393 (Open Web Text)

Max Activating Token Index: 392

Text #2

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.2167. Min Act: -0.1700

Data Index: 4394407 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.1432. Min Act: -0.1700

Data Index: 7247547 (Open Web Text)

Max Activating Token Index: 588

Text #4

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.1148. Min Act: -0.1700

Data Index: 2550742 (Open Web Text)

Max Activating Token Index: 700

Text #5

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.1061. Min Act: -0.1700

Data Index: 7842444 (Open Web Text)

Max Activating Token Index: 264

Text #6

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.1038. Min Act: -0.1700

Data Index: 5620427 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0918. Min Act: -0.1700

Data Index: 1469567 (Open Web Text)

Max Activating Token Index: 453

Text #8

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.1024. Min Act: -0.1700

Data Index: 335032 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0762. Min Act: -0.1700

Data Index: 8014264 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.1008. Min Act: -0.1700

Data Index: 2875992 (Open Web Text)

Max Activating Token Index: 477

Text #11

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0675. Min Act: -0.1700

Data Index: 6766327 (Open Web Text)

Max Activating Token Index: 850

Text #12

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0642. Min Act: -0.1700

Data Index: 4068332 (Open Web Text)

Max Activating Token Index: 794

Text #13

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0144. Min Act: -0.1700

Data Index: 1617170 (Open Web Text)

Max Activating Token Index: 510

Text #14

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0528. Min Act: -0.1700

Data Index: 2207184 (Open Web Text)

Max Activating Token Index: 458

Text #15

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0437. Min Act: -0.1700

Data Index: 3955569 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0501. Min Act: -0.1700

Data Index: 553199 (Open Web Text)

Max Activating Token Index: 1014

Text #17

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0359. Min Act: -0.1700

Data Index: 4721790 (Open Web Text)

Max Activating Token Index: 456

Text #18

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0455. Min Act: -0.1700

Data Index: 5157856 (Open Web Text)

Max Activating Token Index: 1001

Text #19

Max Range: 3.3099. Min Range: -3.3099

Max Act: 3.0448. Min Act: -0.1700

Data Index: 5465340 (Open Web Text)

Max Activating Token Index: 635