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

Dataset: Open Web Text

Neuron 2451 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: 1.4873. Min Range: -1.4873

Max Act: 1.4873. Min Act: -0.1235

Data Index: 3484440 (Open Web Text)

Max Activating Token Index: 659

Text #1

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.4822. Min Act: -0.1235

Data Index: 5629875 (Open Web Text)

Max Activating Token Index: 610

Text #2

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.4542. Min Act: -0.1235

Data Index: 3292941 (Open Web Text)

Max Activating Token Index: 512

Text #3

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.4378. Min Act: -0.1446

Data Index: 8621647 (Open Web Text)

Max Activating Token Index: 535

Text #4

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.4237. Min Act: -0.1235

Data Index: 2275977 (Open Web Text)

Max Activating Token Index: 398

Text #5

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.4218. Min Act: -0.1457

Data Index: 805577 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.4033. Min Act: -0.1235

Data Index: 1574482 (Open Web Text)

Max Activating Token Index: 507

Text #7

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.4037. Min Act: -0.1235

Data Index: 3229243 (Open Web Text)

Max Activating Token Index: 953

Text #8

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3849. Min Act: -0.1235

Data Index: 769968 (Open Web Text)

Max Activating Token Index: 860

Text #9

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3877. Min Act: -0.1235

Data Index: 7066254 (Open Web Text)

Max Activating Token Index: 179

Text #10

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3811. Min Act: -0.1235

Data Index: 8785658 (Open Web Text)

Max Activating Token Index: 483

Text #11

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3805. Min Act: -0.1235

Data Index: 7190965 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3828. Min Act: -0.1235

Data Index: 7843594 (Open Web Text)

Max Activating Token Index: 700

Text #13

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3756. Min Act: -0.1235

Data Index: 1509826 (Open Web Text)

Max Activating Token Index: 901

Text #14

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3779. Min Act: -0.1474

Data Index: 2038200 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3804. Min Act: -0.1235

Data Index: 4496817 (Open Web Text)

Max Activating Token Index: 750

Text #16

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3793. Min Act: -0.1235

Data Index: 6623027 (Open Web Text)

Max Activating Token Index: 913

Text #17

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3747. Min Act: -0.1235

Data Index: 624043 (Open Web Text)

Max Activating Token Index: 444

Text #18

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3684. Min Act: -0.1289

Data Index: 2218356 (Open Web Text)

Max Activating Token Index: 778

Text #19

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3621. Min Act: -0.1235

Data Index: 756140 (Open Web Text)

Max Activating Token Index: 459