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

Dataset: Open Web Text

Neuron 2471 in Layer 3

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: 5.1008. Min Range: -5.1008

Max Act: 5.1008. Min Act: -0.1700

Data Index: 5421985 (Open Web Text)

Max Activating Token Index: 455

Text #1

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.9883. Min Act: -0.1700

Data Index: 5323715 (Open Web Text)

Max Activating Token Index: 155

Text #2

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.9480. Min Act: -0.1700

Data Index: 5869673 (Open Web Text)

Max Activating Token Index: 848

Text #3

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8946. Min Act: -0.1700

Data Index: 3146595 (Open Web Text)

Max Activating Token Index: 463

Text #4

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8953. Min Act: -0.1700

Data Index: 7582970 (Open Web Text)

Max Activating Token Index: 979

Text #5

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8803. Min Act: -0.1700

Data Index: 654723 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8932. Min Act: -0.1700

Data Index: 620679 (Open Web Text)

Max Activating Token Index: 654

Text #7

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8656. Min Act: -0.1700

Data Index: 7938200 (Open Web Text)

Max Activating Token Index: 606

Text #8

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8608. Min Act: -0.1700

Data Index: 99092 (Open Web Text)

Max Activating Token Index: 753

Text #9

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8458. Min Act: -0.1700

Data Index: 8497290 (Open Web Text)

Max Activating Token Index: 460

Text #10

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8353. Min Act: -0.1700

Data Index: 2519300 (Open Web Text)

Max Activating Token Index: 157

Text #11

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.7907. Min Act: -0.1700

Data Index: 8565381 (Open Web Text)

Max Activating Token Index: 132

Text #12

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8086. Min Act: -0.1700

Data Index: 3629391 (Open Web Text)

Max Activating Token Index: 324

Text #13

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8084. Min Act: -0.1700

Data Index: 29511 (Open Web Text)

Max Activating Token Index: 1003

Text #14

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.7877. Min Act: -0.1700

Data Index: 3263447 (Open Web Text)

Max Activating Token Index: 43

Text #15

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.7735. Min Act: -0.1700

Data Index: 5571718 (Open Web Text)

Max Activating Token Index: 826

Text #16

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.8157. Min Act: -0.1700

Data Index: 2350906 (Open Web Text)

Max Activating Token Index: 364

Text #17

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.7754. Min Act: -0.1700

Data Index: 7185305 (Open Web Text)

Max Activating Token Index: 940

Text #18

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.7745. Min Act: -0.1700

Data Index: 4502556 (Open Web Text)

Max Activating Token Index: 78

Text #19

Max Range: 5.1008. Min Range: -5.1008

Max Act: 4.7602. Min Act: -0.1700

Data Index: 8209025 (Open Web Text)

Max Activating Token Index: 396