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

Dataset: Open Web Text

Neuron 2474 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: 3.3096. Min Range: -3.3096

Max Act: 3.2918. Min Act: -0.1700

Data Index: 8335197 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2892. Min Act: -0.1700

Data Index: 508416 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.3004. Min Act: -0.1700

Data Index: 4705481 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.3096. Min Act: -0.1700

Data Index: 2801185 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2734. Min Act: -0.1698

Data Index: 1343709 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2774. Min Act: -0.1700

Data Index: 8527674 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2418. Min Act: -0.1700

Data Index: 1343728 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2355. Min Act: -0.1700

Data Index: 2413620 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2132. Min Act: -0.1700

Data Index: 8557114 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2230. Min Act: -0.1700

Data Index: 508417 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1960. Min Act: -0.1700

Data Index: 7930091 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2039. Min Act: -0.1700

Data Index: 5457946 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1897. Min Act: -0.1700

Data Index: 689889 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1898. Min Act: -0.1700

Data Index: 1718756 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1939. Min Act: -0.1700

Data Index: 3845185 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1542. Min Act: -0.1700

Data Index: 5687627 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1445. Min Act: -0.1700

Data Index: 7455236 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1338. Min Act: -0.1700

Data Index: 2131633 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1334. Min Act: -0.1700

Data Index: 6369992 (Open Web Text)

Max Activating Token Index: 876

Text #19

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1131. Min Act: -0.1700

Data Index: 5831562 (Open Web Text)

Max Activating Token Index: 19