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

Dataset: Open Web Text

Neuron 2634 in Layer 1

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: 1.8077. Min Range: -1.8077

Max Act: 1.8077. Min Act: -0.1700

Data Index: 1017859 (Open Web Text)

Max Activating Token Index: 1015

Text #1

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7623. Min Act: -0.1700

Data Index: 6688369 (Open Web Text)

Max Activating Token Index: 199

Text #2

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7762. Min Act: -0.1700

Data Index: 2580697 (Open Web Text)

Max Activating Token Index: 402

Text #3

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7798. Min Act: -0.1700

Data Index: 1508504 (Open Web Text)

Max Activating Token Index: 463

Text #4

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7753. Min Act: -0.1700

Data Index: 5038968 (Open Web Text)

Max Activating Token Index: 520

Text #5

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7659. Min Act: -0.1698

Data Index: 739514 (Open Web Text)

Max Activating Token Index: 424

Text #6

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7501. Min Act: -0.1700

Data Index: 3898689 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7597. Min Act: -0.1700

Data Index: 3774112 (Open Web Text)

Max Activating Token Index: 144

Text #8

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7453. Min Act: -0.1700

Data Index: 6889413 (Open Web Text)

Max Activating Token Index: 200

Text #9

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7467. Min Act: -0.1700

Data Index: 4485538 (Open Web Text)

Max Activating Token Index: 268

Text #10

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7579. Min Act: -0.1700

Data Index: 8601031 (Open Web Text)

Max Activating Token Index: 678

Text #11

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7465. Min Act: -0.1700

Data Index: 4702048 (Open Web Text)

Max Activating Token Index: 590

Text #12

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7501. Min Act: -0.1700

Data Index: 2558176 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7300. Min Act: -0.1700

Data Index: 8781972 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7324. Min Act: -0.1700

Data Index: 179814 (Open Web Text)

Max Activating Token Index: 571

Text #15

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7363. Min Act: -0.1700

Data Index: 7970890 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7421. Min Act: -0.1700

Data Index: 6203441 (Open Web Text)

Max Activating Token Index: 574

Text #17

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7406. Min Act: -0.1700

Data Index: 7825887 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7375. Min Act: -0.1700

Data Index: 5166070 (Open Web Text)

Max Activating Token Index: 190

Text #19

Max Range: 1.8077. Min Range: -1.8077

Max Act: 1.7353. Min Act: -0.1700

Data Index: 3125380 (Open Web Text)

Max Activating Token Index: 521