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

Dataset: Open Web Text

Neuron 1017 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: 2.9267. Min Range: -2.9267

Max Act: 2.9267. Min Act: -0.1700

Data Index: 3428733 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8693. Min Act: -0.1700

Data Index: 4536725 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8646. Min Act: -0.1700

Data Index: 2859186 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8536. Min Act: -0.1700

Data Index: 1907576 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8461. Min Act: -0.1700

Data Index: 115407 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8509. Min Act: -0.1700

Data Index: 1820423 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8434. Min Act: -0.1700

Data Index: 384875 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8310. Min Act: -0.1700

Data Index: 8038848 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8160. Min Act: -0.1700

Data Index: 427274 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8192. Min Act: -0.1700

Data Index: 8474591 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8148. Min Act: -0.1700

Data Index: 1594509 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8144. Min Act: -0.1700

Data Index: 2447252 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8164. Min Act: -0.1700

Data Index: 3635195 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8243. Min Act: -0.1700

Data Index: 68606 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8161. Min Act: -0.1700

Data Index: 6588107 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8065. Min Act: -0.1700

Data Index: 3911857 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8034. Min Act: -0.1700

Data Index: 1511409 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.7970. Min Act: -0.1700

Data Index: 4613693 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8030. Min Act: -0.1700

Data Index: 1821804 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 2.9267. Min Range: -2.9267

Max Act: 2.8020. Min Act: -0.1700

Data Index: 6387436 (Open Web Text)

Max Activating Token Index: 4