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

Dataset: Open Web Text

Neuron 556 in Layer 4

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: 4.2635. Min Range: -4.2635

Max Act: 4.2635. Min Act: -0.1700

Data Index: 6114038 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.1253. Min Act: -0.1700

Data Index: 404850 (Open Web Text)

Max Activating Token Index: 812

Text #2

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0968. Min Act: -0.1700

Data Index: 5553618 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0905. Min Act: -0.1700

Data Index: 1716327 (Open Web Text)

Max Activating Token Index: 916

Text #4

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0597. Min Act: -0.1700

Data Index: 269514 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0723. Min Act: -0.1700

Data Index: 2997359 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0184. Min Act: -0.1700

Data Index: 6951161 (Open Web Text)

Max Activating Token Index: 941

Text #7

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0289. Min Act: -0.1700

Data Index: 926205 (Open Web Text)

Max Activating Token Index: 779

Text #8

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0399. Min Act: -0.1700

Data Index: 4410010 (Open Web Text)

Max Activating Token Index: 256

Text #9

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0452. Min Act: -0.1700

Data Index: 4497454 (Open Web Text)

Max Activating Token Index: 680

Text #10

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0267. Min Act: -0.1700

Data Index: 1885098 (Open Web Text)

Max Activating Token Index: 692

Text #11

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0535. Min Act: -0.1700

Data Index: 4167344 (Open Web Text)

Max Activating Token Index: 166

Text #12

Max Range: 4.2635. Min Range: -4.2635

Max Act: 3.9819. Min Act: -0.1700

Data Index: 6923409 (Open Web Text)

Max Activating Token Index: 493

Text #13

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0192. Min Act: -0.1700

Data Index: 4968861 (Open Web Text)

Max Activating Token Index: 539

Text #14

Max Range: 4.2635. Min Range: -4.2635

Max Act: 3.9885. Min Act: -0.1700

Data Index: 4226544 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 4.2635. Min Range: -4.2635

Max Act: 3.9982. Min Act: -0.1700

Data Index: 6374588 (Open Web Text)

Max Activating Token Index: 670

Text #16

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0121. Min Act: -0.1700

Data Index: 3750657 (Open Web Text)

Max Activating Token Index: 148

Text #17

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0062. Min Act: -0.1700

Data Index: 2014897 (Open Web Text)

Max Activating Token Index: 842

Text #18

Max Range: 4.2635. Min Range: -4.2635

Max Act: 4.0308. Min Act: -0.1700

Data Index: 2670259 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 4.2635. Min Range: -4.2635

Max Act: 3.9946. Min Act: -0.1700

Data Index: 6844440 (Open Web Text)

Max Activating Token Index: 421