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

Dataset: Open Web Text

Neuron 1072 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: 4.6527. Min Range: -4.6527

Max Act: 4.6527. Min Act: -0.1700

Data Index: 3349549 (Open Web Text)

Max Activating Token Index: 991

Text #1

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.5281. Min Act: -0.1700

Data Index: 2786857 (Open Web Text)

Max Activating Token Index: 152

Text #2

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.5343. Min Act: -0.1700

Data Index: 409080 (Open Web Text)

Max Activating Token Index: 897

Text #3

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.4654. Min Act: -0.1700

Data Index: 6608324 (Open Web Text)

Max Activating Token Index: 377

Text #4

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.4766. Min Act: -0.1700

Data Index: 4652511 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.4780. Min Act: -0.1700

Data Index: 5812164 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.4514. Min Act: -0.1700

Data Index: 5436042 (Open Web Text)

Max Activating Token Index: 120

Text #7

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.4083. Min Act: -0.1700

Data Index: 4417556 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.4439. Min Act: -0.1700

Data Index: 3108666 (Open Web Text)

Max Activating Token Index: 391

Text #9

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.4424. Min Act: -0.1700

Data Index: 6618619 (Open Web Text)

Max Activating Token Index: 865

Text #10

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.4197. Min Act: -0.1700

Data Index: 738900 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.4077. Min Act: -0.1700

Data Index: 1032210 (Open Web Text)

Max Activating Token Index: 707

Text #12

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.4162. Min Act: -0.1700

Data Index: 7536969 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.3871. Min Act: -0.1700

Data Index: 8049369 (Open Web Text)

Max Activating Token Index: 933

Text #14

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.3699. Min Act: -0.1700

Data Index: 6154976 (Open Web Text)

Max Activating Token Index: 291

Text #15

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.3475. Min Act: -0.1700

Data Index: 2927529 (Open Web Text)

Max Activating Token Index: 309

Text #16

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.3328. Min Act: -0.1700

Data Index: 1057145 (Open Web Text)

Max Activating Token Index: 300

Text #17

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.3607. Min Act: -0.1700

Data Index: 3294940 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.3420. Min Act: -0.1700

Data Index: 8750929 (Open Web Text)

Max Activating Token Index: 364

Text #19

Max Range: 4.6527. Min Range: -4.6527

Max Act: 4.3737. Min Act: -0.1700

Data Index: 1057144 (Open Web Text)

Max Activating Token Index: 852