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

Dataset: Open Web Text

Neuron 1539 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: 4.3540. Min Range: -4.3540

Max Act: 4.3146. Min Act: -0.1700

Data Index: 6188389 (Open Web Text)

Max Activating Token Index: 527

Text #1

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.3540. Min Act: -0.1700

Data Index: 1768677 (Open Web Text)

Max Activating Token Index: 802

Text #2

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2959. Min Act: -0.1700

Data Index: 7737908 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2619. Min Act: -0.1700

Data Index: 1083855 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2431. Min Act: -0.1700

Data Index: 4855439 (Open Web Text)

Max Activating Token Index: 554

Text #5

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2774. Min Act: -0.1700

Data Index: 2298791 (Open Web Text)

Max Activating Token Index: 576

Text #6

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2455. Min Act: -0.1700

Data Index: 2323833 (Open Web Text)

Max Activating Token Index: 629

Text #7

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2556. Min Act: -0.1700

Data Index: 6328161 (Open Web Text)

Max Activating Token Index: 576

Text #8

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2639. Min Act: -0.1700

Data Index: 8306753 (Open Web Text)

Max Activating Token Index: 887

Text #9

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2617. Min Act: -0.1700

Data Index: 7982049 (Open Web Text)

Max Activating Token Index: 371

Text #10

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2643. Min Act: -0.1700

Data Index: 2382389 (Open Web Text)

Max Activating Token Index: 238

Text #11

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2099. Min Act: -0.1700

Data Index: 4973470 (Open Web Text)

Max Activating Token Index: 474

Text #12

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2483. Min Act: -0.1700

Data Index: 271411 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2352. Min Act: -0.1700

Data Index: 3051801 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2228. Min Act: -0.1700

Data Index: 7890374 (Open Web Text)

Max Activating Token Index: 878

Text #15

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2490. Min Act: -0.1700

Data Index: 7262910 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2287. Min Act: -0.1700

Data Index: 7182326 (Open Web Text)

Max Activating Token Index: 538

Text #17

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2270. Min Act: -0.1700

Data Index: 2161030 (Open Web Text)

Max Activating Token Index: 293

Text #18

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.1929. Min Act: -0.1700

Data Index: 2097640 (Open Web Text)

Max Activating Token Index: 1004

Text #19

Max Range: 4.3540. Min Range: -4.3540

Max Act: 4.2179. Min Act: -0.1700

Data Index: 2068202 (Open Web Text)

Max Activating Token Index: 656