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

Dataset: Open Web Text

Neuron 1928 in Layer 6

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: 3.9076. Min Range: -3.9076

Max Act: 3.9076. Min Act: -0.1700

Data Index: 3820390 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.8350. Min Act: -0.1700

Data Index: 1694202 (Open Web Text)

Max Activating Token Index: 977

Text #2

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.8580. Min Act: -0.1700

Data Index: 8607987 (Open Web Text)

Max Activating Token Index: 124

Text #3

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.8588. Min Act: -0.1700

Data Index: 2735743 (Open Web Text)

Max Activating Token Index: 783

Text #4

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.8284. Min Act: -0.1700

Data Index: 6715187 (Open Web Text)

Max Activating Token Index: 683

Text #5

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.8115. Min Act: -0.1700

Data Index: 4215733 (Open Web Text)

Max Activating Token Index: 337

Text #6

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.8382. Min Act: -0.1700

Data Index: 5753260 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.8173. Min Act: -0.1700

Data Index: 5981992 (Open Web Text)

Max Activating Token Index: 125

Text #8

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.8260. Min Act: -0.1700

Data Index: 203152 (Open Web Text)

Max Activating Token Index: 995

Text #9

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.7791. Min Act: -0.1700

Data Index: 2237875 (Open Web Text)

Max Activating Token Index: 665

Text #10

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.8086. Min Act: -0.1700

Data Index: 1402437 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.7986. Min Act: -0.1700

Data Index: 5804302 (Open Web Text)

Max Activating Token Index: 390

Text #12

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.7634. Min Act: -0.1700

Data Index: 4189521 (Open Web Text)

Max Activating Token Index: 150

Text #13

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.7861. Min Act: -0.1700

Data Index: 4285786 (Open Web Text)

Max Activating Token Index: 367

Text #14

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.7997. Min Act: -0.1700

Data Index: 2215488 (Open Web Text)

Max Activating Token Index: 812

Text #15

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.7547. Min Act: -0.1700

Data Index: 4730439 (Open Web Text)

Max Activating Token Index: 818

Text #16

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.7548. Min Act: -0.1700

Data Index: 6473003 (Open Web Text)

Max Activating Token Index: 516

Text #17

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.7736. Min Act: -0.1700

Data Index: 6694957 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.7619. Min Act: -0.1700

Data Index: 3265922 (Open Web Text)

Max Activating Token Index: 827

Text #19

Max Range: 3.9076. Min Range: -3.9076

Max Act: 3.7563. Min Act: -0.1700

Data Index: 6710984 (Open Web Text)

Max Activating Token Index: 395