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

Dataset: Open Web Text

Neuron 1581 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: 1.6188. Min Range: -1.6188

Max Act: 1.6188. Min Act: -0.1698

Data Index: 614656 (Open Web Text)

Max Activating Token Index: 153

Text #1

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5722. Min Act: -0.1700

Data Index: 6218327 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5606. Min Act: -0.1700

Data Index: 7689268 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5400. Min Act: -0.1700

Data Index: 4305515 (Open Web Text)

Max Activating Token Index: 589

Text #4

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5340. Min Act: -0.1700

Data Index: 4760010 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5303. Min Act: -0.1700

Data Index: 5448438 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5180. Min Act: -0.1699

Data Index: 7490272 (Open Web Text)

Max Activating Token Index: 254

Text #7

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5253. Min Act: -0.1700

Data Index: 5311958 (Open Web Text)

Max Activating Token Index: 574

Text #8

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5205. Min Act: -0.1700

Data Index: 2582138 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5246. Min Act: -0.1700

Data Index: 4760006 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5313. Min Act: -0.1700

Data Index: 7441260 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5156. Min Act: -0.1700

Data Index: 3785230 (Open Web Text)

Max Activating Token Index: 693

Text #12

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5215. Min Act: -0.1700

Data Index: 8088374 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5165. Min Act: -0.1700

Data Index: 3572689 (Open Web Text)

Max Activating Token Index: 838

Text #14

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5163. Min Act: -0.1700

Data Index: 1457465 (Open Web Text)

Max Activating Token Index: 719

Text #15

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5004. Min Act: -0.1700

Data Index: 1821878 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5105. Min Act: -0.1700

Data Index: 6192737 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5088. Min Act: -0.1700

Data Index: 1057922 (Open Web Text)

Max Activating Token Index: 600

Text #18

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5049. Min Act: -0.1700

Data Index: 8293533 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 1.6188. Min Range: -1.6188

Max Act: 1.5027. Min Act: -0.1700

Data Index: 3605032 (Open Web Text)

Max Activating Token Index: 622