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

Dataset: Open Web Text

Neuron 3028 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: 2.8646. Min Range: -2.8646

Max Act: 2.8646. Min Act: -0.1700

Data Index: 2178310 (Open Web Text)

Max Activating Token Index: 354

Text #1

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7909. Min Act: -0.1700

Data Index: 6844484 (Open Web Text)

Max Activating Token Index: 668

Text #2

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7871. Min Act: -0.1700

Data Index: 7881007 (Open Web Text)

Max Activating Token Index: 378

Text #3

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7878. Min Act: -0.1700

Data Index: 1478670 (Open Web Text)

Max Activating Token Index: 256

Text #4

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.8127. Min Act: -0.1700

Data Index: 4364243 (Open Web Text)

Max Activating Token Index: 83

Text #5

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.8005. Min Act: -0.1700

Data Index: 4306352 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7727. Min Act: -0.1700

Data Index: 6818773 (Open Web Text)

Max Activating Token Index: 940

Text #7

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7916. Min Act: -0.1700

Data Index: 4019022 (Open Web Text)

Max Activating Token Index: 73

Text #8

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7693. Min Act: -0.1700

Data Index: 4161200 (Open Web Text)

Max Activating Token Index: 879

Text #9

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7575. Min Act: -0.1700

Data Index: 6897886 (Open Web Text)

Max Activating Token Index: 342

Text #10

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7445. Min Act: -0.1700

Data Index: 7519354 (Open Web Text)

Max Activating Token Index: 928

Text #11

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7581. Min Act: -0.1700

Data Index: 3651334 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7270. Min Act: -0.1700

Data Index: 1010767 (Open Web Text)

Max Activating Token Index: 311

Text #13

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7082. Min Act: -0.1700

Data Index: 6930776 (Open Web Text)

Max Activating Token Index: 1006

Text #14

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7121. Min Act: -0.1700

Data Index: 5520520 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7375. Min Act: -0.1700

Data Index: 785680 (Open Web Text)

Max Activating Token Index: 801

Text #16

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7313. Min Act: -0.1700

Data Index: 2292934 (Open Web Text)

Max Activating Token Index: 177

Text #17

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7051. Min Act: -0.1700

Data Index: 2372640 (Open Web Text)

Max Activating Token Index: 56

Text #18

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.6986. Min Act: -0.1700

Data Index: 5287294 (Open Web Text)

Max Activating Token Index: 694

Text #19

Max Range: 2.8646. Min Range: -2.8646

Max Act: 2.7088. Min Act: -0.1700

Data Index: 967026 (Open Web Text)

Max Activating Token Index: 665