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

Dataset: Open Web Text

Neuron 1130 in Layer 2

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: 3.9519. Min Range: -3.9519

Max Act: 3.9258. Min Act: -0.1700

Data Index: 5734117 (Open Web Text)

Max Activating Token Index: 412

Text #1

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.9519. Min Act: -0.1700

Data Index: 2919657 (Open Web Text)

Max Activating Token Index: 615

Text #2

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8657. Min Act: -0.1700

Data Index: 2325466 (Open Web Text)

Max Activating Token Index: 187

Text #3

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8768. Min Act: -0.1700

Data Index: 8656826 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8451. Min Act: -0.1700

Data Index: 6910115 (Open Web Text)

Max Activating Token Index: 533

Text #5

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8722. Min Act: -0.1700

Data Index: 2723144 (Open Web Text)

Max Activating Token Index: 529

Text #6

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8367. Min Act: -0.1700

Data Index: 5785548 (Open Web Text)

Max Activating Token Index: 140

Text #7

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8771. Min Act: -0.1700

Data Index: 5618353 (Open Web Text)

Max Activating Token Index: 608

Text #8

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8572. Min Act: -0.1700

Data Index: 4561616 (Open Web Text)

Max Activating Token Index: 815

Text #9

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8119. Min Act: -0.1700

Data Index: 2381759 (Open Web Text)

Max Activating Token Index: 300

Text #10

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8028. Min Act: -0.1700

Data Index: 149934 (Open Web Text)

Max Activating Token Index: 359

Text #11

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8179. Min Act: -0.1700

Data Index: 4411283 (Open Web Text)

Max Activating Token Index: 340

Text #12

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8131. Min Act: -0.1700

Data Index: 2521857 (Open Web Text)

Max Activating Token Index: 268

Text #13

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.7841. Min Act: -0.1700

Data Index: 4544129 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.7873. Min Act: -0.1700

Data Index: 4569971 (Open Web Text)

Max Activating Token Index: 435

Text #15

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.7676. Min Act: -0.1700

Data Index: 5309974 (Open Web Text)

Max Activating Token Index: 350

Text #16

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.8035. Min Act: -0.1700

Data Index: 3698678 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.7914. Min Act: -0.1700

Data Index: 133607 (Open Web Text)

Max Activating Token Index: 570

Text #18

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.7828. Min Act: -0.1700

Data Index: 6058982 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 3.9519. Min Range: -3.9519

Max Act: 3.7720. Min Act: -0.1700

Data Index: 6159833 (Open Web Text)

Max Activating Token Index: 237