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

Dataset: Open Web Text

Neuron 2669 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: 2.9354. Min Range: -2.9354

Max Act: 2.9354. Min Act: -0.1700

Data Index: 8285498 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.9354. Min Act: -0.1700

Data Index: 213595 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.9013. Min Act: -0.1700

Data Index: 8734456 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8932. Min Act: -0.1700

Data Index: 3177161 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8735. Min Act: -0.1700

Data Index: 8200744 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8444. Min Act: -0.1700

Data Index: 3054692 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8449. Min Act: -0.1700

Data Index: 929940 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8290. Min Act: -0.1700

Data Index: 222310 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8076. Min Act: -0.1700

Data Index: 7743231 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8076. Min Act: -0.1700

Data Index: 3666826 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8160. Min Act: -0.1700

Data Index: 7269047 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8141. Min Act: -0.1700

Data Index: 2028444 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8166. Min Act: -0.1700

Data Index: 8342181 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8076. Min Act: -0.1700

Data Index: 6949360 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8076. Min Act: -0.1700

Data Index: 6387709 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8076. Min Act: -0.1700

Data Index: 930947 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8076. Min Act: -0.1700

Data Index: 525651 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8076. Min Act: -0.1700

Data Index: 4860829 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8076. Min Act: -0.1700

Data Index: 2107841 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.8162. Min Act: -0.1700

Data Index: 1102047 (Open Web Text)

Max Activating Token Index: 9