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

Dataset: Open Web Text

Neuron 567 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: 3.3000. Min Range: -3.3000

Max Act: 3.3000. Min Act: -0.1700

Data Index: 5312299 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1871. Min Act: -0.1700

Data Index: 8636594 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1871. Min Act: -0.1700

Data Index: 802513 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1744. Min Act: -0.1700

Data Index: 3838352 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1486. Min Act: -0.1700

Data Index: 3840541 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1446. Min Act: -0.1700

Data Index: 6935504 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1289. Min Act: -0.1700

Data Index: 5234776 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1318. Min Act: -0.1700

Data Index: 7374521 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1318. Min Act: -0.1700

Data Index: 8724852 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1288. Min Act: -0.1700

Data Index: 2087355 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1318. Min Act: -0.1700

Data Index: 4694481 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1318. Min Act: -0.1700

Data Index: 2441946 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1263. Min Act: -0.1700

Data Index: 8759260 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1318. Min Act: -0.1700

Data Index: 2622327 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1156. Min Act: -0.1700

Data Index: 7345191 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1121. Min Act: -0.1700

Data Index: 6935503 (Open Web Text)

Max Activating Token Index: 925

Text #16

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1110. Min Act: -0.1700

Data Index: 3832536 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1137. Min Act: -0.1700

Data Index: 7409072 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.0925. Min Act: -0.1700

Data Index: 6935505 (Open Web Text)

Max Activating Token Index: 422

Text #19

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.0961. Min Act: -0.1700

Data Index: 6940916 (Open Web Text)

Max Activating Token Index: 4