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

Dataset: Open Web Text

Neuron 946 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: 4.6233. Min Range: -4.6233

Max Act: 4.6233. Min Act: -0.1700

Data Index: 4463527 (Open Web Text)

Max Activating Token Index: 789

Text #1

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.4766. Min Act: -0.1700

Data Index: 793370 (Open Web Text)

Max Activating Token Index: 216

Text #2

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.4376. Min Act: -0.1700

Data Index: 4484577 (Open Web Text)

Max Activating Token Index: 675

Text #3

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.3693. Min Act: -0.1700

Data Index: 1422233 (Open Web Text)

Max Activating Token Index: 449

Text #4

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.3534. Min Act: -0.1700

Data Index: 4778050 (Open Web Text)

Max Activating Token Index: 674

Text #5

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.3165. Min Act: -0.1700

Data Index: 8151692 (Open Web Text)

Max Activating Token Index: 555

Text #6

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.3416. Min Act: -0.1700

Data Index: 1090653 (Open Web Text)

Max Activating Token Index: 383

Text #7

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.3085. Min Act: -0.1700

Data Index: 1365675 (Open Web Text)

Max Activating Token Index: 427

Text #8

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2917. Min Act: -0.1700

Data Index: 5972789 (Open Web Text)

Max Activating Token Index: 465

Text #9

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2929. Min Act: -0.1700

Data Index: 8555236 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2610. Min Act: -0.1700

Data Index: 6039374 (Open Web Text)

Max Activating Token Index: 929

Text #11

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2481. Min Act: -0.1700

Data Index: 60205 (Open Web Text)

Max Activating Token Index: 771

Text #12

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2730. Min Act: -0.1700

Data Index: 7238903 (Open Web Text)

Max Activating Token Index: 769

Text #13

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2733. Min Act: -0.1700

Data Index: 4218254 (Open Web Text)

Max Activating Token Index: 258

Text #14

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2571. Min Act: -0.1700

Data Index: 4615588 (Open Web Text)

Max Activating Token Index: 872

Text #15

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2588. Min Act: -0.1700

Data Index: 4269705 (Open Web Text)

Max Activating Token Index: 799

Text #16

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2317. Min Act: -0.1700

Data Index: 5855056 (Open Web Text)

Max Activating Token Index: 979

Text #17

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2053. Min Act: -0.1700

Data Index: 1962772 (Open Web Text)

Max Activating Token Index: 795

Text #18

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2340. Min Act: -0.1700

Data Index: 6154807 (Open Web Text)

Max Activating Token Index: 183

Text #19

Max Range: 4.6233. Min Range: -4.6233

Max Act: 4.2109. Min Act: -0.1700

Data Index: 1359468 (Open Web Text)

Max Activating Token Index: 745