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

Dataset: Open Web Text

Neuron 424 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: 3.9898. Min Range: -3.9898

Max Act: 3.9898. Min Act: -0.1700

Data Index: 5940295 (Open Web Text)

Max Activating Token Index: 983

Text #1

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.9014. Min Act: -0.1700

Data Index: 6639230 (Open Web Text)

Max Activating Token Index: 231

Text #2

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8008. Min Act: -0.1700

Data Index: 1163237 (Open Web Text)

Max Activating Token Index: 707

Text #3

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.7446. Min Act: -0.1700

Data Index: 2580482 (Open Web Text)

Max Activating Token Index: 1014

Text #4

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.7178. Min Act: -0.1700

Data Index: 587159 (Open Web Text)

Max Activating Token Index: 373

Text #5

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6931. Min Act: -0.1700

Data Index: 3587710 (Open Web Text)

Max Activating Token Index: 363

Text #6

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.7132. Min Act: -0.1700

Data Index: 2424408 (Open Web Text)

Max Activating Token Index: 498

Text #7

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.7212. Min Act: -0.1700

Data Index: 1811683 (Open Web Text)

Max Activating Token Index: 436

Text #8

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6658. Min Act: -0.1700

Data Index: 3787628 (Open Web Text)

Max Activating Token Index: 491

Text #9

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6437. Min Act: -0.1700

Data Index: 2991239 (Open Web Text)

Max Activating Token Index: 570

Text #10

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6469. Min Act: -0.1700

Data Index: 1895414 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6641. Min Act: -0.1700

Data Index: 3694573 (Open Web Text)

Max Activating Token Index: 739

Text #12

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6793. Min Act: -0.1700

Data Index: 4435438 (Open Web Text)

Max Activating Token Index: 724

Text #13

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6593. Min Act: -0.1700

Data Index: 6775239 (Open Web Text)

Max Activating Token Index: 86

Text #14

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6563. Min Act: -0.1700

Data Index: 5243053 (Open Web Text)

Max Activating Token Index: 559

Text #15

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6562. Min Act: -0.1700

Data Index: 5332907 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6223. Min Act: -0.1700

Data Index: 2884151 (Open Web Text)

Max Activating Token Index: 632

Text #17

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6403. Min Act: -0.1700

Data Index: 843065 (Open Web Text)

Max Activating Token Index: 756

Text #18

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6284. Min Act: -0.1700

Data Index: 2244442 (Open Web Text)

Max Activating Token Index: 41

Text #19

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.6345. Min Act: -0.1700

Data Index: 347926 (Open Web Text)

Max Activating Token Index: 390