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

Dataset: Open Web Text

Neuron 2429 in Layer 0

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: 3.1405. Min Range: -3.1405

Max Act: 3.1405. Min Act: -0.1700

Data Index: 2880005 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9992. Min Act: -0.1700

Data Index: 5271256 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9670. Min Act: -0.1700

Data Index: 3226260 (Open Web Text)

Max Activating Token Index: 54

Text #3

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9291. Min Act: -0.1700

Data Index: 6638626 (Open Web Text)

Max Activating Token Index: 151

Text #4

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9445. Min Act: -0.1700

Data Index: 484709 (Open Web Text)

Max Activating Token Index: 840

Text #5

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.9255. Min Act: -0.1700

Data Index: 8531601 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8682. Min Act: -0.1700

Data Index: 1243655 (Open Web Text)

Max Activating Token Index: 762

Text #7

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8527. Min Act: -0.1700

Data Index: 6982114 (Open Web Text)

Max Activating Token Index: 96

Text #8

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8597. Min Act: -0.1700

Data Index: 3575401 (Open Web Text)

Max Activating Token Index: 834

Text #9

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8520. Min Act: -0.1700

Data Index: 1554587 (Open Web Text)

Max Activating Token Index: 396

Text #10

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8589. Min Act: -0.1700

Data Index: 447701 (Open Web Text)

Max Activating Token Index: 168

Text #11

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8331. Min Act: -0.1700

Data Index: 7802404 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8445. Min Act: -0.1700

Data Index: 758780 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8219. Min Act: -0.1700

Data Index: 8134611 (Open Web Text)

Max Activating Token Index: 267

Text #14

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8291. Min Act: -0.1700

Data Index: 8213703 (Open Web Text)

Max Activating Token Index: 977

Text #15

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8204. Min Act: -0.1700

Data Index: 5042693 (Open Web Text)

Max Activating Token Index: 665

Text #16

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8204. Min Act: -0.1700

Data Index: 435870 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8320. Min Act: -0.1700

Data Index: 7086067 (Open Web Text)

Max Activating Token Index: 152

Text #18

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8230. Min Act: -0.1700

Data Index: 4673708 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 3.1405. Min Range: -3.1405

Max Act: 2.8275. Min Act: -0.1700

Data Index: 298272 (Open Web Text)

Max Activating Token Index: 8