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

Dataset: Open Web Text

Neuron 832 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: 3.6301. Min Range: -3.6301

Max Act: 3.6301. Min Act: -0.1700

Data Index: 3482752 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5665. Min Act: -0.1700

Data Index: 7615482 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5863. Min Act: -0.1700

Data Index: 1054831 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5664. Min Act: -0.1700

Data Index: 5481374 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5460. Min Act: -0.1700

Data Index: 8128700 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5155. Min Act: -0.1700

Data Index: 6716580 (Open Web Text)

Max Activating Token Index: 878

Text #6

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5564. Min Act: -0.1700

Data Index: 6674375 (Open Web Text)

Max Activating Token Index: 24

Text #7

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5442. Min Act: -0.1700

Data Index: 2292896 (Open Web Text)

Max Activating Token Index: 860

Text #8

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5255. Min Act: -0.1700

Data Index: 6549159 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5472. Min Act: -0.1700

Data Index: 1983134 (Open Web Text)

Max Activating Token Index: 638

Text #10

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5426. Min Act: -0.1700

Data Index: 5883888 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5356. Min Act: -0.1700

Data Index: 120273 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5529. Min Act: -0.1700

Data Index: 1830707 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5102. Min Act: -0.1700

Data Index: 6577148 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5112. Min Act: -0.1700

Data Index: 5310426 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5297. Min Act: -0.1700

Data Index: 5237591 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5167. Min Act: -0.1700

Data Index: 1366792 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5182. Min Act: -0.1700

Data Index: 3636663 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5193. Min Act: -0.1700

Data Index: 7061710 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.6301. Min Range: -3.6301

Max Act: 3.5055. Min Act: -0.1700

Data Index: 4263903 (Open Web Text)

Max Activating Token Index: 7