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

Dataset: Open Web Text

Neuron 2853 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: 3.2665. Min Range: -3.2665

Max Act: 3.2665. Min Act: -0.1700

Data Index: 411578 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2335. Min Act: -0.1700

Data Index: 4315740 (Open Web Text)

Max Activating Token Index: 364

Text #2

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2090. Min Act: -0.1700

Data Index: 2478059 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2137. Min Act: -0.1700

Data Index: 1245250 (Open Web Text)

Max Activating Token Index: 587

Text #4

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2080. Min Act: -0.1700

Data Index: 8082407 (Open Web Text)

Max Activating Token Index: 484

Text #5

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1851. Min Act: -0.1700

Data Index: 3539901 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1723. Min Act: -0.1700

Data Index: 1245248 (Open Web Text)

Max Activating Token Index: 333

Text #7

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1585. Min Act: -0.1700

Data Index: 1245249 (Open Web Text)

Max Activating Token Index: 461

Text #8

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1714. Min Act: -0.1700

Data Index: 4698904 (Open Web Text)

Max Activating Token Index: 733

Text #9

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1641. Min Act: -0.1700

Data Index: 7901364 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1333. Min Act: -0.1700

Data Index: 5179905 (Open Web Text)

Max Activating Token Index: 303

Text #11

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1474. Min Act: -0.1700

Data Index: 1471600 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1428. Min Act: -0.1700

Data Index: 1567436 (Open Web Text)

Max Activating Token Index: 208

Text #13

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1312. Min Act: -0.1700

Data Index: 6448135 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1226. Min Act: -0.1700

Data Index: 2226566 (Open Web Text)

Max Activating Token Index: 136

Text #15

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1128. Min Act: -0.1700

Data Index: 4698905 (Open Web Text)

Max Activating Token Index: 89

Text #16

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.0961. Min Act: -0.1700

Data Index: 7048056 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.0984. Min Act: -0.1700

Data Index: 3539900 (Open Web Text)

Max Activating Token Index: 693

Text #18

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1115. Min Act: -0.1700

Data Index: 990447 (Open Web Text)

Max Activating Token Index: 201

Text #19

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1058. Min Act: -0.1700

Data Index: 7306487 (Open Web Text)

Max Activating Token Index: 92