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

Dataset: Open Web Text

Neuron 2703 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: 4.7231. Min Range: -4.7231

Max Act: 4.7231. Min Act: -0.1700

Data Index: 7439282 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.6868. Min Act: -0.1700

Data Index: 2430931 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.6211. Min Act: -0.1700

Data Index: 768805 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.6071. Min Act: -0.1700

Data Index: 4986618 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5613. Min Act: -0.1700

Data Index: 7438525 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5791. Min Act: -0.1700

Data Index: 8041090 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5630. Min Act: -0.1700

Data Index: 4618926 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5620. Min Act: -0.1700

Data Index: 7719020 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5544. Min Act: -0.1700

Data Index: 5528163 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5519. Min Act: -0.1700

Data Index: 1765204 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5187. Min Act: -0.1700

Data Index: 719587 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5246. Min Act: -0.1700

Data Index: 1457931 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5398. Min Act: -0.1700

Data Index: 682827 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5183. Min Act: -0.1700

Data Index: 5426493 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5388. Min Act: -0.1700

Data Index: 801193 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5207. Min Act: -0.1700

Data Index: 7143400 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5403. Min Act: -0.1700

Data Index: 2435068 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5148. Min Act: -0.1700

Data Index: 2556894 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5388. Min Act: -0.1700

Data Index: 6002048 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.7231. Min Range: -4.7231

Max Act: 4.5108. Min Act: -0.1700

Data Index: 5438116 (Open Web Text)

Max Activating Token Index: 5