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

Dataset: Open Web Text

Neuron 2325 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: 4.9484. Min Range: -4.9484

Max Act: 4.9484. Min Act: -0.1700

Data Index: 3789327 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.8810. Min Act: -0.1700

Data Index: 2722454 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.8392. Min Act: -0.1700

Data Index: 7083975 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7861. Min Act: -0.1700

Data Index: 5896330 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7760. Min Act: -0.1700

Data Index: 6594451 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7374. Min Act: -0.1700

Data Index: 6847618 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7144. Min Act: -0.1700

Data Index: 7983194 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.6954. Min Act: -0.1700

Data Index: 3191613 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7296. Min Act: -0.1700

Data Index: 7599633 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7233. Min Act: -0.1700

Data Index: 6670604 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7011. Min Act: -0.1700

Data Index: 2624191 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7011. Min Act: -0.1700

Data Index: 5835488 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7011. Min Act: -0.1700

Data Index: 8090455 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.6954. Min Act: -0.1700

Data Index: 60924 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.6857. Min Act: -0.1700

Data Index: 3775860 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.6841. Min Act: -0.1700

Data Index: 2423605 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7011. Min Act: -0.1700

Data Index: 3229883 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7011. Min Act: -0.1700

Data Index: 8234601 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.7011. Min Act: -0.1700

Data Index: 5919355 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.9484. Min Range: -4.9484

Max Act: 4.6972. Min Act: -0.1700

Data Index: 8825633 (Open Web Text)

Max Activating Token Index: 4