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

Dataset: Open Web Text

Neuron 2691 in Layer 4

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: 2.8410. Min Range: -2.8410

Max Act: 2.8410. Min Act: -0.1700

Data Index: 382691 (Open Web Text)

Max Activating Token Index: 574

Text #1

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7969. Min Act: -0.1700

Data Index: 4022892 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.8313. Min Act: -0.1700

Data Index: 8710448 (Open Web Text)

Max Activating Token Index: 84

Text #3

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.8164. Min Act: -0.1700

Data Index: 5386406 (Open Web Text)

Max Activating Token Index: 769

Text #4

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7996. Min Act: -0.1700

Data Index: 7978138 (Open Web Text)

Max Activating Token Index: 836

Text #5

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7835. Min Act: -0.1700

Data Index: 7087509 (Open Web Text)

Max Activating Token Index: 346

Text #6

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7778. Min Act: -0.1700

Data Index: 2621246 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7828. Min Act: -0.1700

Data Index: 6074802 (Open Web Text)

Max Activating Token Index: 495

Text #8

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7807. Min Act: -0.1700

Data Index: 6967749 (Open Web Text)

Max Activating Token Index: 290

Text #9

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7460. Min Act: -0.1700

Data Index: 6314903 (Open Web Text)

Max Activating Token Index: 532

Text #10

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7530. Min Act: -0.1700

Data Index: 7506697 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7457. Min Act: -0.1700

Data Index: 1146812 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7245. Min Act: -0.1700

Data Index: 3684647 (Open Web Text)

Max Activating Token Index: 304

Text #13

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7441. Min Act: -0.1700

Data Index: 8633374 (Open Web Text)

Max Activating Token Index: 124

Text #14

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7268. Min Act: -0.1700

Data Index: 1480811 (Open Web Text)

Max Activating Token Index: 267

Text #15

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7547. Min Act: -0.1700

Data Index: 2954347 (Open Web Text)

Max Activating Token Index: 871

Text #16

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7275. Min Act: -0.1700

Data Index: 37964 (Open Web Text)

Max Activating Token Index: 238

Text #17

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7292. Min Act: -0.1700

Data Index: 6573045 (Open Web Text)

Max Activating Token Index: 501

Text #18

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7290. Min Act: -0.1700

Data Index: 4374672 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 2.8410. Min Range: -2.8410

Max Act: 2.7059. Min Act: -0.1700

Data Index: 5119779 (Open Web Text)

Max Activating Token Index: 348