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

Dataset: Open Web Text

Neuron 643 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: 3.8397. Min Range: -3.8397

Max Act: 3.8397. Min Act: -0.1700

Data Index: 7305215 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.8049. Min Act: -0.1700

Data Index: 3538196 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.8010. Min Act: -0.1700

Data Index: 5848105 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.7489. Min Act: -0.1700

Data Index: 8211066 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.7212. Min Act: -0.1700

Data Index: 2402043 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.7011. Min Act: -0.1700

Data Index: 6356137 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.6637. Min Act: -0.1700

Data Index: 1104235 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.6700. Min Act: -0.1700

Data Index: 6722848 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1171563 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.6182. Min Act: -0.1700

Data Index: 7087348 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.6120. Min Act: -0.1700

Data Index: 4861446 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5784. Min Act: -0.1700

Data Index: 2151597 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5881. Min Act: -0.1700

Data Index: 7317255 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5884. Min Act: -0.1700

Data Index: 2035215 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5771. Min Act: -0.1700

Data Index: 2959591 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5536. Min Act: -0.1700

Data Index: 575532 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5657. Min Act: -0.1700

Data Index: 5304828 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5722. Min Act: -0.1700

Data Index: 5976894 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5549. Min Act: -0.1700

Data Index: 4211055 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.8397. Min Range: -3.8397

Max Act: 3.5749. Min Act: -0.1700

Data Index: 408201 (Open Web Text)

Max Activating Token Index: 8