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

Dataset: Open Web Text

Neuron 1572 in Layer 5

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: 4.6014. Min Range: -4.6014

Max Act: 4.6014. Min Act: -0.1700

Data Index: 2327586 (Open Web Text)

Max Activating Token Index: 369

Text #1

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.3404. Min Act: -0.1700

Data Index: 1649501 (Open Web Text)

Max Activating Token Index: 243

Text #2

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2911. Min Act: -0.1700

Data Index: 5759659 (Open Web Text)

Max Activating Token Index: 996

Text #3

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.3181. Min Act: -0.1700

Data Index: 8618956 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2830. Min Act: -0.1700

Data Index: 5982397 (Open Web Text)

Max Activating Token Index: 335

Text #5

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2404. Min Act: -0.1700

Data Index: 3224683 (Open Web Text)

Max Activating Token Index: 541

Text #6

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2563. Min Act: -0.1700

Data Index: 2628705 (Open Web Text)

Max Activating Token Index: 707

Text #7

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2508. Min Act: -0.1700

Data Index: 2172616 (Open Web Text)

Max Activating Token Index: 712

Text #8

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2171. Min Act: -0.1700

Data Index: 2963897 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2338. Min Act: -0.1700

Data Index: 4336769 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2396. Min Act: -0.1700

Data Index: 4279559 (Open Web Text)

Max Activating Token Index: 544

Text #11

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2157. Min Act: -0.1700

Data Index: 3339742 (Open Web Text)

Max Activating Token Index: 407

Text #12

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2297. Min Act: -0.1700

Data Index: 3054820 (Open Web Text)

Max Activating Token Index: 383

Text #13

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2139. Min Act: -0.1700

Data Index: 4953796 (Open Web Text)

Max Activating Token Index: 916

Text #14

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2437. Min Act: -0.1700

Data Index: 3727806 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.1946. Min Act: -0.1700

Data Index: 1785296 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2317. Min Act: -0.1700

Data Index: 7335869 (Open Web Text)

Max Activating Token Index: 999

Text #17

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2164. Min Act: -0.1700

Data Index: 868721 (Open Web Text)

Max Activating Token Index: 468

Text #18

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2019. Min Act: -0.1700

Data Index: 8138998 (Open Web Text)

Max Activating Token Index: 316

Text #19

Max Range: 4.6014. Min Range: -4.6014

Max Act: 4.2280. Min Act: -0.1700

Data Index: 8213936 (Open Web Text)

Max Activating Token Index: 590