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

Dataset: Open Web Text

Neuron 409 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: 4.7853. Min Range: -4.7853

Max Act: 4.7691. Min Act: -0.1700

Data Index: 8032933 (Open Web Text)

Max Activating Token Index: 138

Text #1

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.7853. Min Act: -0.1700

Data Index: 2157350 (Open Web Text)

Max Activating Token Index: 841

Text #2

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.7221. Min Act: -0.1700

Data Index: 8711837 (Open Web Text)

Max Activating Token Index: 1004

Text #3

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6891. Min Act: -0.1700

Data Index: 5845725 (Open Web Text)

Max Activating Token Index: 728

Text #4

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6473. Min Act: -0.1700

Data Index: 4321898 (Open Web Text)

Max Activating Token Index: 720

Text #5

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6869. Min Act: -0.1700

Data Index: 2243581 (Open Web Text)

Max Activating Token Index: 254

Text #6

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6513. Min Act: -0.1700

Data Index: 3317809 (Open Web Text)

Max Activating Token Index: 778

Text #7

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6253. Min Act: -0.1700

Data Index: 8311105 (Open Web Text)

Max Activating Token Index: 824

Text #8

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6541. Min Act: -0.1700

Data Index: 3035811 (Open Web Text)

Max Activating Token Index: 803

Text #9

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6235. Min Act: -0.1700

Data Index: 2836704 (Open Web Text)

Max Activating Token Index: 811

Text #10

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6525. Min Act: -0.1700

Data Index: 6502731 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6805. Min Act: -0.1700

Data Index: 5774797 (Open Web Text)

Max Activating Token Index: 387

Text #12

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6031. Min Act: -0.1700

Data Index: 6751421 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6194. Min Act: -0.1700

Data Index: 1625287 (Open Web Text)

Max Activating Token Index: 360

Text #14

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6348. Min Act: -0.1700

Data Index: 2802627 (Open Web Text)

Max Activating Token Index: 520

Text #15

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6227. Min Act: -0.1700

Data Index: 2288064 (Open Web Text)

Max Activating Token Index: 672

Text #16

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6498. Min Act: -0.1700

Data Index: 4512422 (Open Web Text)

Max Activating Token Index: 642

Text #17

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6136. Min Act: -0.1700

Data Index: 4213187 (Open Web Text)

Max Activating Token Index: 856

Text #18

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6246. Min Act: -0.1700

Data Index: 4195681 (Open Web Text)

Max Activating Token Index: 851

Text #19

Max Range: 4.7853. Min Range: -4.7853

Max Act: 4.6212. Min Act: -0.1700

Data Index: 3966608 (Open Web Text)

Max Activating Token Index: 962