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

Dataset: Open Web Text

Neuron 1492 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: 3.7968. Min Range: -3.7968

Max Act: 3.7968. Min Act: -0.1700

Data Index: 7975325 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.7142. Min Act: -0.1700

Data Index: 6633480 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6561. Min Act: -0.1700

Data Index: 8363379 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6750. Min Act: -0.1700

Data Index: 1527123 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6344. Min Act: -0.1700

Data Index: 8124746 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6344. Min Act: -0.1700

Data Index: 3412836 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6411. Min Act: -0.1700

Data Index: 3774250 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6348. Min Act: -0.1700

Data Index: 8487467 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6352. Min Act: -0.1700

Data Index: 8128012 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6052. Min Act: -0.1700

Data Index: 6231939 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6102. Min Act: -0.1700

Data Index: 6434268 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6176. Min Act: -0.1700

Data Index: 6548970 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6106. Min Act: -0.1700

Data Index: 420876 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6035. Min Act: -0.1700

Data Index: 4725451 (Open Web Text)

Max Activating Token Index: 306

Text #14

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6120. Min Act: -0.1700

Data Index: 6952289 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6052. Min Act: -0.1700

Data Index: 7672458 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.5735. Min Act: -0.1700

Data Index: 4898419 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.5724. Min Act: -0.1700

Data Index: 283305 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.5657. Min Act: -0.1700

Data Index: 2289732 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.5819. Min Act: -0.1700

Data Index: 4918576 (Open Web Text)

Max Activating Token Index: 7