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

Dataset: Open Web Text

Neuron 877 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: 3.0354. Min Range: -3.0354

Max Act: 3.0354. Min Act: -0.1700

Data Index: 2512665 (Open Web Text)

Max Activating Token Index: 535

Text #1

Max Range: 3.0354. Min Range: -3.0354

Max Act: 3.0043. Min Act: -0.1700

Data Index: 8362051 (Open Web Text)

Max Activating Token Index: 92

Text #2

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.9895. Min Act: -0.1700

Data Index: 5954172 (Open Web Text)

Max Activating Token Index: 259

Text #3

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.9847. Min Act: -0.1700

Data Index: 3558570 (Open Web Text)

Max Activating Token Index: 773

Text #4

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.9755. Min Act: -0.1700

Data Index: 4447881 (Open Web Text)

Max Activating Token Index: 70

Text #5

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.9343. Min Act: -0.1700

Data Index: 4998174 (Open Web Text)

Max Activating Token Index: 384

Text #6

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.9207. Min Act: -0.1700

Data Index: 5180514 (Open Web Text)

Max Activating Token Index: 375

Text #7

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.9151. Min Act: -0.1700

Data Index: 6620130 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.9050. Min Act: -0.1700

Data Index: 3670383 (Open Web Text)

Max Activating Token Index: 300

Text #9

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.9079. Min Act: -0.1700

Data Index: 848261 (Open Web Text)

Max Activating Token Index: 573

Text #10

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.8597. Min Act: -0.1700

Data Index: 7132428 (Open Web Text)

Max Activating Token Index: 786

Text #11

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.8425. Min Act: -0.1700

Data Index: 6682935 (Open Web Text)

Max Activating Token Index: 161

Text #12

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.8490. Min Act: -0.1700

Data Index: 2203624 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.8555. Min Act: -0.1700

Data Index: 3736551 (Open Web Text)

Max Activating Token Index: 905

Text #14

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.8323. Min Act: -0.1700

Data Index: 964345 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.8314. Min Act: -0.1700

Data Index: 4019096 (Open Web Text)

Max Activating Token Index: 113

Text #16

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.7918. Min Act: -0.1700

Data Index: 1979337 (Open Web Text)

Max Activating Token Index: 406

Text #17

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.8237. Min Act: -0.1700

Data Index: 2965234 (Open Web Text)

Max Activating Token Index: 217

Text #18

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.7812. Min Act: -0.1700

Data Index: 1328279 (Open Web Text)

Max Activating Token Index: 418

Text #19

Max Range: 3.0354. Min Range: -3.0354

Max Act: 2.8030. Min Act: -0.1700

Data Index: 2270734 (Open Web Text)

Max Activating Token Index: 846