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

Dataset: Open Web Text

Neuron 489 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: 2.8109. Min Range: -2.8109

Max Act: 2.8045. Min Act: -0.1700

Data Index: 51387 (Open Web Text)

Max Activating Token Index: 757

Text #1

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.8006. Min Act: -0.1700

Data Index: 4025925 (Open Web Text)

Max Activating Token Index: 841

Text #2

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.8109. Min Act: -0.1700

Data Index: 795037 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.7605. Min Act: -0.1700

Data Index: 57727 (Open Web Text)

Max Activating Token Index: 210

Text #4

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.7321. Min Act: -0.1700

Data Index: 7109913 (Open Web Text)

Max Activating Token Index: 747

Text #5

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.7363. Min Act: -0.1700

Data Index: 3980868 (Open Web Text)

Max Activating Token Index: 84

Text #6

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.7093. Min Act: -0.1700

Data Index: 6907563 (Open Web Text)

Max Activating Token Index: 80

Text #7

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.7256. Min Act: -0.1700

Data Index: 522513 (Open Web Text)

Max Activating Token Index: 664

Text #8

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.7302. Min Act: -0.1700

Data Index: 8614399 (Open Web Text)

Max Activating Token Index: 802

Text #9

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.7134. Min Act: -0.1700

Data Index: 3222008 (Open Web Text)

Max Activating Token Index: 380

Text #10

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.7012. Min Act: -0.1700

Data Index: 3981508 (Open Web Text)

Max Activating Token Index: 213

Text #11

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.6849. Min Act: -0.1700

Data Index: 6437771 (Open Web Text)

Max Activating Token Index: 579

Text #12

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.6710. Min Act: -0.1700

Data Index: 5384520 (Open Web Text)

Max Activating Token Index: 345

Text #13

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.6716. Min Act: -0.1700

Data Index: 1372696 (Open Web Text)

Max Activating Token Index: 540

Text #14

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.6534. Min Act: -0.1700

Data Index: 3279553 (Open Web Text)

Max Activating Token Index: 808

Text #15

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.6494. Min Act: -0.1700

Data Index: 7721214 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.6476. Min Act: -0.1700

Data Index: 3428919 (Open Web Text)

Max Activating Token Index: 604

Text #17

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.6389. Min Act: -0.1700

Data Index: 7792608 (Open Web Text)

Max Activating Token Index: 161

Text #18

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.6231. Min Act: -0.1700

Data Index: 3610915 (Open Web Text)

Max Activating Token Index: 144

Text #19

Max Range: 2.8109. Min Range: -2.8109

Max Act: 2.6270. Min Act: -0.1700

Data Index: 5178257 (Open Web Text)

Max Activating Token Index: 111