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

Dataset: Open Web Text

Neuron 151 in Layer 5

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: 3.9777. Min Range: -3.9777

Max Act: 3.9777. Min Act: -0.1700

Data Index: 8084969 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.9226. Min Act: -0.1700

Data Index: 6496922 (Open Web Text)

Max Activating Token Index: 868

Text #2

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.9004. Min Act: -0.1700

Data Index: 2127293 (Open Web Text)

Max Activating Token Index: 328

Text #3

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.8974. Min Act: -0.1700

Data Index: 1759323 (Open Web Text)

Max Activating Token Index: 489

Text #4

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.8878. Min Act: -0.1700

Data Index: 350842 (Open Web Text)

Max Activating Token Index: 383

Text #5

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.8855. Min Act: -0.1700

Data Index: 3493333 (Open Web Text)

Max Activating Token Index: 650

Text #6

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.8303. Min Act: -0.1700

Data Index: 7611594 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.8219. Min Act: -0.1700

Data Index: 3498709 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.8180. Min Act: -0.1700

Data Index: 8135563 (Open Web Text)

Max Activating Token Index: 599

Text #9

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7868. Min Act: -0.1700

Data Index: 2992272 (Open Web Text)

Max Activating Token Index: 438

Text #10

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7903. Min Act: -0.1700

Data Index: 6039888 (Open Web Text)

Max Activating Token Index: 189

Text #11

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7436. Min Act: -0.1700

Data Index: 2940396 (Open Web Text)

Max Activating Token Index: 854

Text #12

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7736. Min Act: -0.1700

Data Index: 2219332 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7491. Min Act: -0.1700

Data Index: 7943073 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7514. Min Act: -0.1700

Data Index: 6338345 (Open Web Text)

Max Activating Token Index: 329

Text #15

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7495. Min Act: -0.1700

Data Index: 2579989 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7691. Min Act: -0.1700

Data Index: 7086921 (Open Web Text)

Max Activating Token Index: 821

Text #17

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7328. Min Act: -0.1700

Data Index: 6565129 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7175. Min Act: -0.1700

Data Index: 6864098 (Open Web Text)

Max Activating Token Index: 550

Text #19

Max Range: 3.9777. Min Range: -3.9777

Max Act: 3.7335. Min Act: -0.1700

Data Index: 6928306 (Open Web Text)

Max Activating Token Index: 1009