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

Dataset: Open Web Text

Neuron 2125 in Layer 6

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: 8.6437. Min Range: -8.6437

Max Act: 8.6437. Min Act: -0.1700

Data Index: 4624021 (Open Web Text)

Max Activating Token Index: 942

Text #1

Max Range: 8.6437. Min Range: -8.6437

Max Act: 8.3147. Min Act: -0.1700

Data Index: 7225118 (Open Web Text)

Max Activating Token Index: 464

Text #2

Max Range: 8.6437. Min Range: -8.6437

Max Act: 8.1270. Min Act: -0.1700

Data Index: 6042985 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 8.6437. Min Range: -8.6437

Max Act: 8.1794. Min Act: -0.1700

Data Index: 7947555 (Open Web Text)

Max Activating Token Index: 1013

Text #4

Max Range: 8.6437. Min Range: -8.6437

Max Act: 8.0574. Min Act: -0.1700

Data Index: 97922 (Open Web Text)

Max Activating Token Index: 820

Text #5

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.9476. Min Act: -0.1700

Data Index: 6974450 (Open Web Text)

Max Activating Token Index: 731

Text #6

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.9422. Min Act: -0.1700

Data Index: 5322646 (Open Web Text)

Max Activating Token Index: 984

Text #7

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.9321. Min Act: -0.1700

Data Index: 2421050 (Open Web Text)

Max Activating Token Index: 199

Text #8

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.7363. Min Act: -0.1700

Data Index: 6633451 (Open Web Text)

Max Activating Token Index: 945

Text #9

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.7986. Min Act: -0.1700

Data Index: 6897449 (Open Web Text)

Max Activating Token Index: 234

Text #10

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.8396. Min Act: -0.1700

Data Index: 1878175 (Open Web Text)

Max Activating Token Index: 740

Text #11

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.6867. Min Act: -0.1700

Data Index: 4778137 (Open Web Text)

Max Activating Token Index: 472

Text #12

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.7760. Min Act: -0.1700

Data Index: 2346978 (Open Web Text)

Max Activating Token Index: 689

Text #13

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.7108. Min Act: -0.1700

Data Index: 8727337 (Open Web Text)

Max Activating Token Index: 579

Text #14

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.6534. Min Act: -0.1700

Data Index: 6808771 (Open Web Text)

Max Activating Token Index: 170

Text #15

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.7702. Min Act: -0.1700

Data Index: 3374561 (Open Web Text)

Max Activating Token Index: 707

Text #16

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.6992. Min Act: -0.1700

Data Index: 265259 (Open Web Text)

Max Activating Token Index: 934

Text #17

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.6199. Min Act: -0.1700

Data Index: 5658090 (Open Web Text)

Max Activating Token Index: 1016

Text #18

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.6332. Min Act: -0.1700

Data Index: 3016098 (Open Web Text)

Max Activating Token Index: 1005

Text #19

Max Range: 8.6437. Min Range: -8.6437

Max Act: 7.5340. Min Act: -0.1700

Data Index: 345582 (Open Web Text)

Max Activating Token Index: 351