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

Dataset: Open Web Text

Neuron 675 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: 3.0272. Min Range: -3.0272

Max Act: 3.0272. Min Act: -0.1700

Data Index: 3592030 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.0272. Min Range: -3.0272

Max Act: 3.0067. Min Act: -0.1700

Data Index: 6912669 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9939. Min Act: -0.1700

Data Index: 4139764 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.0272. Min Range: -3.0272

Max Act: 3.0076. Min Act: -0.1700

Data Index: 3368979 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.0272. Min Range: -3.0272

Max Act: 3.0008. Min Act: -0.1700

Data Index: 7433939 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.0272. Min Range: -3.0272

Max Act: 3.0034. Min Act: -0.1700

Data Index: 6934488 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9673. Min Act: -0.1700

Data Index: 1016966 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9686. Min Act: -0.1700

Data Index: 243043 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9784. Min Act: -0.1700

Data Index: 2069545 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9738. Min Act: -0.1700

Data Index: 1017249 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9663. Min Act: -0.1700

Data Index: 237378 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9612. Min Act: -0.1700

Data Index: 8137480 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9697. Min Act: -0.1700

Data Index: 908486 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9868. Min Act: -0.1700

Data Index: 8426910 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9545. Min Act: -0.1700

Data Index: 2036900 (Open Web Text)

Max Activating Token Index: 795

Text #15

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9638. Min Act: -0.1700

Data Index: 8758971 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9395. Min Act: -0.1700

Data Index: 75851 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9372. Min Act: -0.1700

Data Index: 5100057 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9345. Min Act: -0.1700

Data Index: 6568582 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.0272. Min Range: -3.0272

Max Act: 2.9254. Min Act: -0.1700

Data Index: 6631800 (Open Web Text)

Max Activating Token Index: 44