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

Dataset: Open Web Text

Neuron 197 in Layer 0

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: 2.4316. Min Range: -2.4316

Max Act: 2.4240. Min Act: -0.1700

Data Index: 890376 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.4240. Min Act: -0.1700

Data Index: 7957705 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.4240. Min Act: -0.1700

Data Index: 4447705 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.4316. Min Act: -0.1700

Data Index: 5575197 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.4240. Min Act: -0.1700

Data Index: 3732447 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.4240. Min Act: -0.1700

Data Index: 1681350 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.4240. Min Act: -0.1700

Data Index: 187961 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3944. Min Act: -0.1700

Data Index: 8044418 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3758. Min Act: -0.1700

Data Index: 1496349 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3817. Min Act: -0.1700

Data Index: 2201687 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3803. Min Act: -0.1700

Data Index: 4323516 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3691. Min Act: -0.1700

Data Index: 261804 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3777. Min Act: -0.1700

Data Index: 1293145 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3817. Min Act: -0.1700

Data Index: 2528493 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3567. Min Act: -0.1700

Data Index: 4644483 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3754. Min Act: -0.1700

Data Index: 1686565 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3795. Min Act: -0.1700

Data Index: 355710 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3739. Min Act: -0.1700

Data Index: 4814910 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3681. Min Act: -0.1700

Data Index: 4599247 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.4316. Min Range: -2.4316

Max Act: 2.3668. Min Act: -0.1700

Data Index: 5541491 (Open Web Text)

Max Activating Token Index: 4