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

Dataset: Open Web Text

Neuron 2380 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: 2.9700. Min Range: -2.9700

Max Act: 2.9698. Min Act: -0.1700

Data Index: 1017638 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9700. Min Act: -0.1700

Data Index: 932836 (Open Web Text)

Max Activating Token Index: 27

Text #2

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9526. Min Act: -0.1700

Data Index: 2256216 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9580. Min Act: -0.1700

Data Index: 7653620 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9517. Min Act: -0.1700

Data Index: 8262871 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9442. Min Act: -0.1700

Data Index: 924928 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9382. Min Act: -0.1700

Data Index: 7277978 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9363. Min Act: -0.1700

Data Index: 2387866 (Open Web Text)

Max Activating Token Index: 71

Text #8

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9170. Min Act: -0.1700

Data Index: 3139028 (Open Web Text)

Max Activating Token Index: 547

Text #9

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9330. Min Act: -0.1700

Data Index: 4917153 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9248. Min Act: -0.1700

Data Index: 8010836 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9125. Min Act: -0.1700

Data Index: 5669326 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.9143. Min Act: -0.1700

Data Index: 3853113 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8854. Min Act: -0.1700

Data Index: 8185619 (Open Web Text)

Max Activating Token Index: 685

Text #14

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8854. Min Act: -0.1700

Data Index: 2484226 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8826. Min Act: -0.1700

Data Index: 1554240 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8992. Min Act: -0.1700

Data Index: 3561012 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8906. Min Act: -0.1700

Data Index: 6685313 (Open Web Text)

Max Activating Token Index: 40

Text #18

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8972. Min Act: -0.1700

Data Index: 3089448 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 2.9700. Min Range: -2.9700

Max Act: 2.8902. Min Act: -0.1700

Data Index: 687726 (Open Web Text)

Max Activating Token Index: 5