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

Dataset: Open Web Text

Neuron 2182 in Layer 4

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: 3.9502. Min Range: -3.9502

Max Act: 3.9502. Min Act: -0.1700

Data Index: 1872471 (Open Web Text)

Max Activating Token Index: 537

Text #1

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.9492. Min Act: -0.1700

Data Index: 6510055 (Open Web Text)

Max Activating Token Index: 504

Text #2

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.8545. Min Act: -0.1700

Data Index: 1256395 (Open Web Text)

Max Activating Token Index: 69

Text #3

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.8494. Min Act: -0.1700

Data Index: 8512062 (Open Web Text)

Max Activating Token Index: 827

Text #4

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.8432. Min Act: -0.1700

Data Index: 272981 (Open Web Text)

Max Activating Token Index: 669

Text #5

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.8186. Min Act: -0.1700

Data Index: 253957 (Open Web Text)

Max Activating Token Index: 1016

Text #6

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.8253. Min Act: -0.1700

Data Index: 3275931 (Open Web Text)

Max Activating Token Index: 146

Text #7

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.8106. Min Act: -0.1700

Data Index: 5902397 (Open Web Text)

Max Activating Token Index: 937

Text #8

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7991. Min Act: -0.1700

Data Index: 8805634 (Open Web Text)

Max Activating Token Index: 693

Text #9

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.8042. Min Act: -0.1700

Data Index: 3731182 (Open Web Text)

Max Activating Token Index: 786

Text #10

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7966. Min Act: -0.1700

Data Index: 3953526 (Open Web Text)

Max Activating Token Index: 773

Text #11

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7853. Min Act: -0.1700

Data Index: 2033157 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7644. Min Act: -0.1700

Data Index: 5089722 (Open Web Text)

Max Activating Token Index: 982

Text #13

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7609. Min Act: -0.1700

Data Index: 1714517 (Open Web Text)

Max Activating Token Index: 584

Text #14

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7687. Min Act: -0.1700

Data Index: 6444414 (Open Web Text)

Max Activating Token Index: 804

Text #15

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7361. Min Act: -0.1700

Data Index: 4009533 (Open Web Text)

Max Activating Token Index: 216

Text #16

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7640. Min Act: -0.1700

Data Index: 1040241 (Open Web Text)

Max Activating Token Index: 418

Text #17

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7553. Min Act: -0.1700

Data Index: 3769849 (Open Web Text)

Max Activating Token Index: 322

Text #18

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7393. Min Act: -0.1700

Data Index: 5463597 (Open Web Text)

Max Activating Token Index: 753

Text #19

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7110. Min Act: -0.1700

Data Index: 5779935 (Open Web Text)

Max Activating Token Index: 982