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

Dataset: Open Web Text

Neuron 1307 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: 3.1421. Min Range: -3.1421

Max Act: 3.1421. Min Act: -0.1700

Data Index: 615785 (Open Web Text)

Max Activating Token Index: 916

Text #1

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0981. Min Act: -0.1700

Data Index: 111053 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0602. Min Act: -0.1700

Data Index: 5451776 (Open Web Text)

Max Activating Token Index: 186

Text #3

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0387. Min Act: -0.1700

Data Index: 1513367 (Open Web Text)

Max Activating Token Index: 988

Text #4

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0335. Min Act: -0.1700

Data Index: 3645986 (Open Web Text)

Max Activating Token Index: 1016

Text #5

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0747. Min Act: -0.1700

Data Index: 5902609 (Open Web Text)

Max Activating Token Index: 951

Text #6

Max Range: 3.1421. Min Range: -3.1421

Max Act: 2.9883. Min Act: -0.1700

Data Index: 6904487 (Open Web Text)

Max Activating Token Index: 182

Text #7

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0160. Min Act: -0.1700

Data Index: 4713446 (Open Web Text)

Max Activating Token Index: 324

Text #8

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0186. Min Act: -0.1700

Data Index: 8003283 (Open Web Text)

Max Activating Token Index: 750

Text #9

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0354. Min Act: -0.1700

Data Index: 5136770 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0662. Min Act: -0.1700

Data Index: 2960519 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 3.1421. Min Range: -3.1421

Max Act: 2.9706. Min Act: -0.1700

Data Index: 5908102 (Open Web Text)

Max Activating Token Index: 469

Text #12

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0112. Min Act: -0.1700

Data Index: 602797 (Open Web Text)

Max Activating Token Index: 882

Text #13

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0188. Min Act: -0.1700

Data Index: 7752247 (Open Web Text)

Max Activating Token Index: 568

Text #14

Max Range: 3.1421. Min Range: -3.1421

Max Act: 2.9706. Min Act: -0.1700

Data Index: 3959790 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 3.1421. Min Range: -3.1421

Max Act: 2.9914. Min Act: -0.1700

Data Index: 1137955 (Open Web Text)

Max Activating Token Index: 493

Text #16

Max Range: 3.1421. Min Range: -3.1421

Max Act: 2.9579. Min Act: -0.1700

Data Index: 5290250 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 3.1421. Min Range: -3.1421

Max Act: 2.9577. Min Act: -0.1700

Data Index: 267068 (Open Web Text)

Max Activating Token Index: 845

Text #18

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0529. Min Act: -0.1700

Data Index: 566394 (Open Web Text)

Max Activating Token Index: 566

Text #19

Max Range: 3.1421. Min Range: -3.1421

Max Act: 3.0126. Min Act: -0.1700

Data Index: 4348231 (Open Web Text)

Max Activating Token Index: 151