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

Dataset: Open Web Text

Neuron 1120 in Layer 5

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: 5.7725. Min Range: -5.7725

Max Act: 5.7725. Min Act: -0.1700

Data Index: 2268865 (Open Web Text)

Max Activating Token Index: 756

Text #1

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6313. Min Act: -0.1700

Data Index: 3969042 (Open Web Text)

Max Activating Token Index: 809

Text #2

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6070. Min Act: -0.1700

Data Index: 2462729 (Open Web Text)

Max Activating Token Index: 960

Text #3

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.5752. Min Act: -0.1700

Data Index: 5739434 (Open Web Text)

Max Activating Token Index: 506

Text #4

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.5706. Min Act: -0.1700

Data Index: 1122238 (Open Web Text)

Max Activating Token Index: 673

Text #5

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.5464. Min Act: -0.1700

Data Index: 6480857 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.5331. Min Act: -0.1700

Data Index: 1460417 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.4408. Min Act: -0.1700

Data Index: 4587252 (Open Web Text)

Max Activating Token Index: 789

Text #8

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.4655. Min Act: -0.1700

Data Index: 7378876 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.4159. Min Act: -0.1700

Data Index: 3159221 (Open Web Text)

Max Activating Token Index: 810

Text #10

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.4201. Min Act: -0.1700

Data Index: 3556973 (Open Web Text)

Max Activating Token Index: 712

Text #11

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.4719. Min Act: -0.1700

Data Index: 788995 (Open Web Text)

Max Activating Token Index: 673

Text #12

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.3544. Min Act: -0.1700

Data Index: 7677257 (Open Web Text)

Max Activating Token Index: 743

Text #13

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.3985. Min Act: -0.1700

Data Index: 3296919 (Open Web Text)

Max Activating Token Index: 503

Text #14

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.3620. Min Act: -0.1700

Data Index: 4904314 (Open Web Text)

Max Activating Token Index: 660

Text #15

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.3892. Min Act: -0.1700

Data Index: 6520124 (Open Web Text)

Max Activating Token Index: 902

Text #16

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.3791. Min Act: -0.1700

Data Index: 371601 (Open Web Text)

Max Activating Token Index: 883

Text #17

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.3759. Min Act: -0.1700

Data Index: 6201496 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.3295. Min Act: -0.1700

Data Index: 4186339 (Open Web Text)

Max Activating Token Index: 848

Text #19

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.3324. Min Act: -0.1700

Data Index: 4418281 (Open Web Text)

Max Activating Token Index: 739