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

Dataset: Open Web Text

Neuron 2175 in Layer 6

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: 3.2288. Min Range: -3.2288

Max Act: 3.2115. Min Act: -0.1700

Data Index: 8261829 (Open Web Text)

Max Activating Token Index: 844

Text #1

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.2288. Min Act: -0.1700

Data Index: 139755 (Open Web Text)

Max Activating Token Index: 785

Text #2

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1822. Min Act: -0.1700

Data Index: 5758785 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1749. Min Act: -0.1700

Data Index: 8349625 (Open Web Text)

Max Activating Token Index: 539

Text #4

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1618. Min Act: -0.1700

Data Index: 8681710 (Open Web Text)

Max Activating Token Index: 957

Text #5

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1675. Min Act: -0.1700

Data Index: 7717827 (Open Web Text)

Max Activating Token Index: 332

Text #6

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1723. Min Act: -0.1700

Data Index: 1643618 (Open Web Text)

Max Activating Token Index: 224

Text #7

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1307. Min Act: -0.1700

Data Index: 1135945 (Open Web Text)

Max Activating Token Index: 456

Text #8

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1251. Min Act: -0.1700

Data Index: 7990048 (Open Web Text)

Max Activating Token Index: 640

Text #9

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1098. Min Act: -0.1700

Data Index: 50256 (Open Web Text)

Max Activating Token Index: 660

Text #10

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1144. Min Act: -0.1700

Data Index: 7018015 (Open Web Text)

Max Activating Token Index: 185

Text #11

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0982. Min Act: -0.1700

Data Index: 4366706 (Open Web Text)

Max Activating Token Index: 663

Text #12

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0994. Min Act: -0.1700

Data Index: 2845631 (Open Web Text)

Max Activating Token Index: 172

Text #13

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0918. Min Act: -0.1700

Data Index: 7465698 (Open Web Text)

Max Activating Token Index: 513

Text #14

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0912. Min Act: -0.1700

Data Index: 5201530 (Open Web Text)

Max Activating Token Index: 841

Text #15

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0742. Min Act: -0.1700

Data Index: 19215 (Open Web Text)

Max Activating Token Index: 458

Text #16

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0928. Min Act: -0.1700

Data Index: 8176815 (Open Web Text)

Max Activating Token Index: 615

Text #17

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0679. Min Act: -0.1700

Data Index: 2566657 (Open Web Text)

Max Activating Token Index: 258

Text #18

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0759. Min Act: -0.1700

Data Index: 3691983 (Open Web Text)

Max Activating Token Index: 395

Text #19

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0784. Min Act: -0.1700

Data Index: 4784221 (Open Web Text)

Max Activating Token Index: 783