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

Dataset: Open Web Text

Neuron 509 in Layer 2

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: 4.3238. Min Range: -4.3238

Max Act: 4.3090. Min Act: -0.1700

Data Index: 2827223 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.3238. Min Act: -0.1700

Data Index: 5349245 (Open Web Text)

Max Activating Token Index: 935

Text #2

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2736. Min Act: -0.1700

Data Index: 7206906 (Open Web Text)

Max Activating Token Index: 992

Text #3

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2313. Min Act: -0.1700

Data Index: 1579682 (Open Web Text)

Max Activating Token Index: 887

Text #4

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2287. Min Act: -0.1700

Data Index: 2898874 (Open Web Text)

Max Activating Token Index: 723

Text #5

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2671. Min Act: -0.1700

Data Index: 4482608 (Open Web Text)

Max Activating Token Index: 994

Text #6

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2137. Min Act: -0.1700

Data Index: 3584210 (Open Web Text)

Max Activating Token Index: 275

Text #7

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2445. Min Act: -0.1700

Data Index: 3537493 (Open Web Text)

Max Activating Token Index: 262

Text #8

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2077. Min Act: -0.1700

Data Index: 7501876 (Open Web Text)

Max Activating Token Index: 143

Text #9

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2326. Min Act: -0.1700

Data Index: 7513654 (Open Web Text)

Max Activating Token Index: 866

Text #10

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2361. Min Act: -0.1700

Data Index: 8302051 (Open Web Text)

Max Activating Token Index: 151

Text #11

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2220. Min Act: -0.1700

Data Index: 8334801 (Open Web Text)

Max Activating Token Index: 501

Text #12

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.1787. Min Act: -0.1700

Data Index: 8421096 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2261. Min Act: -0.1700

Data Index: 6772140 (Open Web Text)

Max Activating Token Index: 966

Text #14

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.1908. Min Act: -0.1700

Data Index: 6589502 (Open Web Text)

Max Activating Token Index: 584

Text #15

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2084. Min Act: -0.1700

Data Index: 3261087 (Open Web Text)

Max Activating Token Index: 182

Text #16

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2085. Min Act: -0.1700

Data Index: 4743129 (Open Web Text)

Max Activating Token Index: 309

Text #17

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.1786. Min Act: -0.1700

Data Index: 4914708 (Open Web Text)

Max Activating Token Index: 820

Text #18

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.1882. Min Act: -0.1700

Data Index: 5115450 (Open Web Text)

Max Activating Token Index: 722

Text #19

Max Range: 4.3238. Min Range: -4.3238

Max Act: 4.2021. Min Act: -0.1700

Data Index: 1495367 (Open Web Text)

Max Activating Token Index: 729