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

Dataset: Open Web Text

Neuron 1827 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: 3.9478. Min Range: -3.9478

Max Act: 3.9478. Min Act: -0.1700

Data Index: 1757690 (Open Web Text)

Max Activating Token Index: 969

Text #1

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.8153. Min Act: -0.1700

Data Index: 7121617 (Open Web Text)

Max Activating Token Index: 728

Text #2

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7699. Min Act: -0.1700

Data Index: 7355469 (Open Web Text)

Max Activating Token Index: 634

Text #3

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.8077. Min Act: -0.1700

Data Index: 2566189 (Open Web Text)

Max Activating Token Index: 543

Text #4

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7731. Min Act: -0.1700

Data Index: 2438462 (Open Web Text)

Max Activating Token Index: 529

Text #5

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7512. Min Act: -0.1700

Data Index: 8290653 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7485. Min Act: -0.1700

Data Index: 3597351 (Open Web Text)

Max Activating Token Index: 935

Text #7

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7269. Min Act: -0.1700

Data Index: 767586 (Open Web Text)

Max Activating Token Index: 115

Text #8

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7269. Min Act: -0.1700

Data Index: 85243 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7270. Min Act: -0.1700

Data Index: 7517726 (Open Web Text)

Max Activating Token Index: 673

Text #10

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7099. Min Act: -0.1700

Data Index: 7797462 (Open Web Text)

Max Activating Token Index: 272

Text #11

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7054. Min Act: -0.1700

Data Index: 1470215 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.6943. Min Act: -0.1700

Data Index: 3976165 (Open Web Text)

Max Activating Token Index: 592

Text #13

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7246. Min Act: -0.1700

Data Index: 7392370 (Open Web Text)

Max Activating Token Index: 794

Text #14

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7009. Min Act: -0.1700

Data Index: 5321025 (Open Web Text)

Max Activating Token Index: 771

Text #15

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.7052. Min Act: -0.1700

Data Index: 263891 (Open Web Text)

Max Activating Token Index: 344

Text #16

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.6907. Min Act: -0.1700

Data Index: 2177159 (Open Web Text)

Max Activating Token Index: 140

Text #17

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.6739. Min Act: -0.1700

Data Index: 2405610 (Open Web Text)

Max Activating Token Index: 866

Text #18

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.6977. Min Act: -0.1700

Data Index: 569290 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 3.9478. Min Range: -3.9478

Max Act: 3.6763. Min Act: -0.1700

Data Index: 8294995 (Open Web Text)

Max Activating Token Index: 632