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

Dataset: Open Web Text

Neuron 1654 in Layer 1

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: 1.7640. Min Range: -1.7640

Max Act: 1.7582. Min Act: -0.1700

Data Index: 2899954 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.7582. Min Act: -0.1700

Data Index: 4317628 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.7640. Min Act: -0.1700

Data Index: 501220 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.7640. Min Act: -0.1700

Data Index: 2928883 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.7640. Min Act: -0.1700

Data Index: 3685535 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.7441. Min Act: -0.1700

Data Index: 6332447 (Open Web Text)

Max Activating Token Index: 53

Text #6

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.7345. Min Act: -0.1700

Data Index: 8467638 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.7214. Min Act: -0.1700

Data Index: 1292356 (Open Web Text)

Max Activating Token Index: 38

Text #8

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.7154. Min Act: -0.1700

Data Index: 7844229 (Open Web Text)

Max Activating Token Index: 156

Text #9

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.7034. Min Act: -0.1700

Data Index: 771185 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.6872. Min Act: -0.1700

Data Index: 6157968 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.6832. Min Act: -0.1700

Data Index: 4384478 (Open Web Text)

Max Activating Token Index: 102

Text #12

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.6892. Min Act: -0.1700

Data Index: 1051746 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.6816. Min Act: -0.1700

Data Index: 8553451 (Open Web Text)

Max Activating Token Index: 112

Text #14

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.6803. Min Act: -0.1700

Data Index: 287294 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.6829. Min Act: -0.1700

Data Index: 1169752 (Open Web Text)

Max Activating Token Index: 34

Text #16

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.6748. Min Act: -0.1700

Data Index: 7888433 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.6699. Min Act: -0.1700

Data Index: 6937952 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.6797. Min Act: -0.1700

Data Index: 2754639 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.7640. Min Range: -1.7640

Max Act: 1.6710. Min Act: -0.1700

Data Index: 1050489 (Open Web Text)

Max Activating Token Index: 12