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

Dataset: Open Web Text

Neuron 376 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: 4.6858. Min Range: -4.6858

Max Act: 4.6755. Min Act: -0.1700

Data Index: 8798602 (Open Web Text)

Max Activating Token Index: 655

Text #1

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.6355. Min Act: -0.1700

Data Index: 439967 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.6858. Min Act: -0.1700

Data Index: 358880 (Open Web Text)

Max Activating Token Index: 229

Text #3

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.4786. Min Act: -0.1700

Data Index: 2535046 (Open Web Text)

Max Activating Token Index: 516

Text #4

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.4785. Min Act: -0.1700

Data Index: 7872785 (Open Web Text)

Max Activating Token Index: 640

Text #5

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.4080. Min Act: -0.1700

Data Index: 5544410 (Open Web Text)

Max Activating Token Index: 988

Text #6

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.4108. Min Act: -0.1700

Data Index: 3464430 (Open Web Text)

Max Activating Token Index: 851

Text #7

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3923. Min Act: -0.1700

Data Index: 4416560 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.4023. Min Act: -0.1700

Data Index: 4456957 (Open Web Text)

Max Activating Token Index: 264

Text #9

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.4053. Min Act: -0.1700

Data Index: 5660032 (Open Web Text)

Max Activating Token Index: 426

Text #10

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3967. Min Act: -0.1700

Data Index: 1922299 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3982. Min Act: -0.1700

Data Index: 2336255 (Open Web Text)

Max Activating Token Index: 727

Text #12

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3524. Min Act: -0.1700

Data Index: 5828876 (Open Web Text)

Max Activating Token Index: 880

Text #13

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3532. Min Act: -0.1700

Data Index: 6452571 (Open Web Text)

Max Activating Token Index: 120

Text #14

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3637. Min Act: -0.1700

Data Index: 6683189 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3741. Min Act: -0.1700

Data Index: 1587360 (Open Web Text)

Max Activating Token Index: 145

Text #16

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3636. Min Act: -0.1700

Data Index: 4836668 (Open Web Text)

Max Activating Token Index: 827

Text #17

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3600. Min Act: -0.1700

Data Index: 7711524 (Open Web Text)

Max Activating Token Index: 72

Text #18

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3377. Min Act: -0.1700

Data Index: 3282179 (Open Web Text)

Max Activating Token Index: 872

Text #19

Max Range: 4.6858. Min Range: -4.6858

Max Act: 4.3253. Min Act: -0.1700

Data Index: 3435002 (Open Web Text)

Max Activating Token Index: 1000