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

Dataset: Open Web Text

Neuron 331 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: 3.4548. Min Range: -3.4548

Max Act: 3.4548. Min Act: -0.1700

Data Index: 20826 (Open Web Text)

Max Activating Token Index: 710

Text #1

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.4191. Min Act: -0.1700

Data Index: 4912787 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2819. Min Act: -0.1700

Data Index: 3574015 (Open Web Text)

Max Activating Token Index: 370

Text #3

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2802. Min Act: -0.1700

Data Index: 5451614 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2616. Min Act: -0.1700

Data Index: 7697832 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2560. Min Act: -0.1700

Data Index: 4229370 (Open Web Text)

Max Activating Token Index: 190

Text #6

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2522. Min Act: -0.1700

Data Index: 1739441 (Open Web Text)

Max Activating Token Index: 690

Text #7

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2280. Min Act: -0.1700

Data Index: 8827813 (Open Web Text)

Max Activating Token Index: 230

Text #8

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2264. Min Act: -0.1700

Data Index: 6374893 (Open Web Text)

Max Activating Token Index: 1016

Text #9

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2249. Min Act: -0.1700

Data Index: 6782302 (Open Web Text)

Max Activating Token Index: 256

Text #10

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1696. Min Act: -0.1700

Data Index: 3490783 (Open Web Text)

Max Activating Token Index: 421

Text #11

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1977. Min Act: -0.1700

Data Index: 1480168 (Open Web Text)

Max Activating Token Index: 77

Text #12

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1884. Min Act: -0.1700

Data Index: 3919375 (Open Web Text)

Max Activating Token Index: 297

Text #13

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2130. Min Act: -0.1700

Data Index: 558767 (Open Web Text)

Max Activating Token Index: 985

Text #14

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1888. Min Act: -0.1700

Data Index: 3711794 (Open Web Text)

Max Activating Token Index: 572

Text #15

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1873. Min Act: -0.1700

Data Index: 5262437 (Open Web Text)

Max Activating Token Index: 440

Text #16

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2125. Min Act: -0.1700

Data Index: 3075066 (Open Web Text)

Max Activating Token Index: 709

Text #17

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1846. Min Act: -0.1700

Data Index: 5396506 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1502. Min Act: -0.1700

Data Index: 939473 (Open Web Text)

Max Activating Token Index: 580

Text #19

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1626. Min Act: -0.1700

Data Index: 5396529 (Open Web Text)

Max Activating Token Index: 124