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

Dataset: Open Web Text

Neuron 1210 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: 1.7846. Min Range: -1.7846

Max Act: 1.7846. Min Act: -0.1700

Data Index: 7085881 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7704. Min Act: -0.1700

Data Index: 7601132 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7484. Min Act: -0.1700

Data Index: 5183758 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7621. Min Act: -0.1700

Data Index: 8503159 (Open Web Text)

Max Activating Token Index: 209

Text #4

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7621. Min Act: -0.1700

Data Index: 5030999 (Open Web Text)

Max Activating Token Index: 558

Text #5

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7602. Min Act: -0.1700

Data Index: 3056418 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7569. Min Act: -0.1700

Data Index: 7366346 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7562. Min Act: -0.1700

Data Index: 4049515 (Open Web Text)

Max Activating Token Index: 644

Text #8

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7441. Min Act: -0.1700

Data Index: 7187851 (Open Web Text)

Max Activating Token Index: 732

Text #9

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7418. Min Act: -0.1700

Data Index: 8458383 (Open Web Text)

Max Activating Token Index: 987

Text #10

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7389. Min Act: -0.1700

Data Index: 6844285 (Open Web Text)

Max Activating Token Index: 219

Text #11

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7416. Min Act: -0.1700

Data Index: 33715 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7336. Min Act: -0.1700

Data Index: 2991761 (Open Web Text)

Max Activating Token Index: 387

Text #13

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7314. Min Act: -0.1700

Data Index: 4913045 (Open Web Text)

Max Activating Token Index: 160

Text #14

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7310. Min Act: -0.1700

Data Index: 4380250 (Open Web Text)

Max Activating Token Index: 238

Text #15

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7214. Min Act: -0.1699

Data Index: 5633665 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7303. Min Act: -0.1700

Data Index: 2856988 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7264. Min Act: -0.1700

Data Index: 4480453 (Open Web Text)

Max Activating Token Index: 112

Text #18

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7168. Min Act: -0.1700

Data Index: 956179 (Open Web Text)

Max Activating Token Index: 211

Text #19

Max Range: 1.7846. Min Range: -1.7846

Max Act: 1.7080. Min Act: -0.1700

Data Index: 372268 (Open Web Text)

Max Activating Token Index: 154