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

Dataset: Open Web Text

Neuron 253 in Layer 3

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: 3.5721. Min Range: -3.5721

Max Act: 3.5721. Min Act: -0.1700

Data Index: 3326393 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.5553. Min Act: -0.1700

Data Index: 6344137 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.5345. Min Act: -0.1700

Data Index: 1868798 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.5475. Min Act: -0.1700

Data Index: 242984 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.5345. Min Act: -0.1700

Data Index: 3882129 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.5229. Min Act: -0.1700

Data Index: 8294776 (Open Web Text)

Max Activating Token Index: 34

Text #6

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.5123. Min Act: -0.1700

Data Index: 3518924 (Open Web Text)

Max Activating Token Index: 253

Text #7

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.5121. Min Act: -0.1700

Data Index: 4083392 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.5043. Min Act: -0.1700

Data Index: 2075831 (Open Web Text)

Max Activating Token Index: 98

Text #9

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.4864. Min Act: -0.1700

Data Index: 2579812 (Open Web Text)

Max Activating Token Index: 766

Text #10

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.4883. Min Act: -0.1700

Data Index: 3158683 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.5009. Min Act: -0.1700

Data Index: 2114566 (Open Web Text)

Max Activating Token Index: 48

Text #12

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.4894. Min Act: -0.1700

Data Index: 7423496 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.4704. Min Act: -0.1700

Data Index: 7392036 (Open Web Text)

Max Activating Token Index: 164

Text #14

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.4712. Min Act: -0.1700

Data Index: 1727020 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.4677. Min Act: -0.1700

Data Index: 4493770 (Open Web Text)

Max Activating Token Index: 354

Text #16

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.4759. Min Act: -0.1700

Data Index: 8367293 (Open Web Text)

Max Activating Token Index: 292

Text #17

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.4923. Min Act: -0.1700

Data Index: 5266358 (Open Web Text)

Max Activating Token Index: 86

Text #18

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.4494. Min Act: -0.1700

Data Index: 3342365 (Open Web Text)

Max Activating Token Index: 808

Text #19

Max Range: 3.5721. Min Range: -3.5721

Max Act: 3.4481. Min Act: -0.1700

Data Index: 5821780 (Open Web Text)

Max Activating Token Index: 336