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

Dataset: Open Web Text

Neuron 1558 in Layer 4

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: 3.7611. Min Range: -3.7611

Max Act: 3.7611. Min Act: -0.1700

Data Index: 2809834 (Open Web Text)

Max Activating Token Index: 611

Text #1

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.7166. Min Act: -0.1700

Data Index: 7008406 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.6721. Min Act: -0.1700

Data Index: 220416 (Open Web Text)

Max Activating Token Index: 625

Text #3

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.6767. Min Act: -0.1700

Data Index: 3482840 (Open Web Text)

Max Activating Token Index: 355

Text #4

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.6342. Min Act: -0.1700

Data Index: 2584801 (Open Web Text)

Max Activating Token Index: 801

Text #5

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.6352. Min Act: -0.1700

Data Index: 377561 (Open Web Text)

Max Activating Token Index: 603

Text #6

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.6384. Min Act: -0.1700

Data Index: 4236682 (Open Web Text)

Max Activating Token Index: 195

Text #7

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5939. Min Act: -0.1700

Data Index: 4061276 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.6239. Min Act: -0.1700

Data Index: 594444 (Open Web Text)

Max Activating Token Index: 606

Text #9

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5976. Min Act: -0.1700

Data Index: 2978384 (Open Web Text)

Max Activating Token Index: 991

Text #10

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.6037. Min Act: -0.1700

Data Index: 5862336 (Open Web Text)

Max Activating Token Index: 814

Text #11

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5814. Min Act: -0.1700

Data Index: 7548877 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5863. Min Act: -0.1700

Data Index: 3251020 (Open Web Text)

Max Activating Token Index: 933

Text #13

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5742. Min Act: -0.1700

Data Index: 5432800 (Open Web Text)

Max Activating Token Index: 459

Text #14

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5688. Min Act: -0.1700

Data Index: 2248716 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5713. Min Act: -0.1700

Data Index: 1939188 (Open Web Text)

Max Activating Token Index: 910

Text #16

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5724. Min Act: -0.1700

Data Index: 7652925 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5801. Min Act: -0.1700

Data Index: 4458050 (Open Web Text)

Max Activating Token Index: 69

Text #18

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5743. Min Act: -0.1700

Data Index: 8719937 (Open Web Text)

Max Activating Token Index: 685

Text #19

Max Range: 3.7611. Min Range: -3.7611

Max Act: 3.5756. Min Act: -0.1700

Data Index: 8734997 (Open Web Text)

Max Activating Token Index: 200