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

Dataset: Open Web Text

Neuron 2631 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: 3.7975. Min Range: -3.7975

Max Act: 3.7975. Min Act: -0.1700

Data Index: 1340319 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.5872. Min Act: -0.1700

Data Index: 6723350 (Open Web Text)

Max Activating Token Index: 709

Text #2

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.6219. Min Act: -0.1700

Data Index: 5409297 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.5431. Min Act: -0.1700

Data Index: 7961713 (Open Web Text)

Max Activating Token Index: 685

Text #4

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.6376. Min Act: -0.1700

Data Index: 7537958 (Open Web Text)

Max Activating Token Index: 874

Text #5

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.5351. Min Act: -0.1700

Data Index: 422151 (Open Web Text)

Max Activating Token Index: 844

Text #6

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.5355. Min Act: -0.1700

Data Index: 1652024 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.4978. Min Act: -0.1700

Data Index: 1589543 (Open Web Text)

Max Activating Token Index: 954

Text #8

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.5319. Min Act: -0.1700

Data Index: 7982529 (Open Web Text)

Max Activating Token Index: 249

Text #9

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.5175. Min Act: -0.1700

Data Index: 7643233 (Open Web Text)

Max Activating Token Index: 984

Text #10

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.5310. Min Act: -0.1700

Data Index: 2690848 (Open Web Text)

Max Activating Token Index: 113

Text #11

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.4911. Min Act: -0.1700

Data Index: 7420910 (Open Web Text)

Max Activating Token Index: 391

Text #12

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.5270. Min Act: -0.1700

Data Index: 2867479 (Open Web Text)

Max Activating Token Index: 592

Text #13

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.4878. Min Act: -0.1700

Data Index: 1798788 (Open Web Text)

Max Activating Token Index: 670

Text #14

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.4765. Min Act: -0.1700

Data Index: 4812869 (Open Web Text)

Max Activating Token Index: 178

Text #15

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.4808. Min Act: -0.1700

Data Index: 7635072 (Open Web Text)

Max Activating Token Index: 644

Text #16

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.5121. Min Act: -0.1700

Data Index: 4902038 (Open Web Text)

Max Activating Token Index: 28

Text #17

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.4748. Min Act: -0.1700

Data Index: 5803889 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.4785. Min Act: -0.1700

Data Index: 8399364 (Open Web Text)

Max Activating Token Index: 495

Text #19

Max Range: 3.7975. Min Range: -3.7975

Max Act: 3.4432. Min Act: -0.1700

Data Index: 7269197 (Open Web Text)

Max Activating Token Index: 564