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

Dataset: Open Web Text

Neuron 1485 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: 3.7004. Min Range: -3.7004

Max Act: 3.7004. Min Act: -0.1700

Data Index: 620336 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6358. Min Act: -0.1700

Data Index: 2791974 (Open Web Text)

Max Activating Token Index: 960

Text #2

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6693. Min Act: -0.1700

Data Index: 2065244 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6399. Min Act: -0.1700

Data Index: 1109507 (Open Web Text)

Max Activating Token Index: 378

Text #4

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6662. Min Act: -0.1700

Data Index: 5644376 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6274. Min Act: -0.1700

Data Index: 8474690 (Open Web Text)

Max Activating Token Index: 963

Text #6

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6426. Min Act: -0.1700

Data Index: 6158302 (Open Web Text)

Max Activating Token Index: 135

Text #7

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6376. Min Act: -0.1700

Data Index: 1902246 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6410. Min Act: -0.1700

Data Index: 5866796 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6288. Min Act: -0.1700

Data Index: 4521027 (Open Web Text)

Max Activating Token Index: 748

Text #10

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6317. Min Act: -0.1700

Data Index: 1525751 (Open Web Text)

Max Activating Token Index: 689

Text #11

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6480. Min Act: -0.1700

Data Index: 7470240 (Open Web Text)

Max Activating Token Index: 842

Text #12

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6168. Min Act: -0.1700

Data Index: 3121121 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6051. Min Act: -0.1700

Data Index: 836180 (Open Web Text)

Max Activating Token Index: 855

Text #14

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6086. Min Act: -0.1700

Data Index: 562665 (Open Web Text)

Max Activating Token Index: 739

Text #15

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6034. Min Act: -0.1700

Data Index: 2198739 (Open Web Text)

Max Activating Token Index: 356

Text #16

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.5803. Min Act: -0.1700

Data Index: 5066707 (Open Web Text)

Max Activating Token Index: 486

Text #17

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.5743. Min Act: -0.1700

Data Index: 5461151 (Open Web Text)

Max Activating Token Index: 418

Text #18

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.5941. Min Act: -0.1700

Data Index: 6110968 (Open Web Text)

Max Activating Token Index: 562

Text #19

Max Range: 3.7004. Min Range: -3.7004

Max Act: 3.6204. Min Act: -0.1700

Data Index: 6118647 (Open Web Text)

Max Activating Token Index: 187