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

Dataset: Open Web Text

Neuron 2240 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: 3.1996. Min Range: -3.1996

Max Act: 3.1887. Min Act: -0.1700

Data Index: 6863813 (Open Web Text)

Max Activating Token Index: 401

Text #1

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.1996. Min Act: -0.1700

Data Index: 2401852 (Open Web Text)

Max Activating Token Index: 79

Text #2

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.0498. Min Act: -0.1700

Data Index: 5949201 (Open Web Text)

Max Activating Token Index: 934

Text #3

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.0271. Min Act: -0.1700

Data Index: 8389771 (Open Web Text)

Max Activating Token Index: 537

Text #4

Max Range: 3.1996. Min Range: -3.1996

Max Act: 3.0207. Min Act: -0.1700

Data Index: 5173997 (Open Web Text)

Max Activating Token Index: 74

Text #5

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.9860. Min Act: -0.1700

Data Index: 4229093 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.9484. Min Act: -0.1700

Data Index: 6853598 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.9537. Min Act: -0.1700

Data Index: 5744082 (Open Web Text)

Max Activating Token Index: 503

Text #8

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.9309. Min Act: -0.1700

Data Index: 6799833 (Open Web Text)

Max Activating Token Index: 242

Text #9

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.8910. Min Act: -0.1700

Data Index: 659255 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.9170. Min Act: -0.1700

Data Index: 3743799 (Open Web Text)

Max Activating Token Index: 984

Text #11

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.9373. Min Act: -0.1700

Data Index: 1290182 (Open Web Text)

Max Activating Token Index: 501

Text #12

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.9299. Min Act: -0.1700

Data Index: 8671641 (Open Web Text)

Max Activating Token Index: 632

Text #13

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.8930. Min Act: -0.1700

Data Index: 4090978 (Open Web Text)

Max Activating Token Index: 177

Text #14

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.8827. Min Act: -0.1700

Data Index: 3978591 (Open Web Text)

Max Activating Token Index: 217

Text #15

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.8891. Min Act: -0.1700

Data Index: 3859712 (Open Web Text)

Max Activating Token Index: 294

Text #16

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.8867. Min Act: -0.1700

Data Index: 517762 (Open Web Text)

Max Activating Token Index: 31

Text #17

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.8716. Min Act: -0.1700

Data Index: 1688358 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.8795. Min Act: -0.1700

Data Index: 5837157 (Open Web Text)

Max Activating Token Index: 494

Text #19

Max Range: 3.1996. Min Range: -3.1996

Max Act: 2.8871. Min Act: -0.1700

Data Index: 573065 (Open Web Text)

Max Activating Token Index: 100