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

Dataset: Open Web Text

Neuron 1866 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: 4.5713. Min Range: -4.5713

Max Act: 4.5713. Min Act: -0.1700

Data Index: 3651278 (Open Web Text)

Max Activating Token Index: 241

Text #1

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.5136. Min Act: -0.1700

Data Index: 5817660 (Open Web Text)

Max Activating Token Index: 610

Text #2

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.4714. Min Act: -0.1700

Data Index: 6095703 (Open Web Text)

Max Activating Token Index: 100

Text #3

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.4649. Min Act: -0.1700

Data Index: 1738327 (Open Web Text)

Max Activating Token Index: 966

Text #4

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.4650. Min Act: -0.1700

Data Index: 457755 (Open Web Text)

Max Activating Token Index: 781

Text #5

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.4346. Min Act: -0.1700

Data Index: 5455721 (Open Web Text)

Max Activating Token Index: 529

Text #6

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.4243. Min Act: -0.1700

Data Index: 657586 (Open Web Text)

Max Activating Token Index: 593

Text #7

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.2891. Min Act: -0.1700

Data Index: 1879689 (Open Web Text)

Max Activating Token Index: 827

Text #8

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.3905. Min Act: -0.1700

Data Index: 1388585 (Open Web Text)

Max Activating Token Index: 154

Text #9

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.3694. Min Act: -0.1700

Data Index: 6139169 (Open Web Text)

Max Activating Token Index: 975

Text #10

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.3578. Min Act: -0.1700

Data Index: 7527876 (Open Web Text)

Max Activating Token Index: 413

Text #11

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.3404. Min Act: -0.1700

Data Index: 8124094 (Open Web Text)

Max Activating Token Index: 507

Text #12

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.3372. Min Act: -0.1700

Data Index: 4356516 (Open Web Text)

Max Activating Token Index: 502

Text #13

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.3127. Min Act: -0.1700

Data Index: 8686486 (Open Web Text)

Max Activating Token Index: 917

Text #14

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.3174. Min Act: -0.1700

Data Index: 8429312 (Open Web Text)

Max Activating Token Index: 690

Text #15

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.3413. Min Act: -0.1700

Data Index: 639355 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.2853. Min Act: -0.1700

Data Index: 1636508 (Open Web Text)

Max Activating Token Index: 938

Text #17

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.3489. Min Act: -0.1700

Data Index: 4623612 (Open Web Text)

Max Activating Token Index: 482

Text #18

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.2305. Min Act: -0.1700

Data Index: 5852620 (Open Web Text)

Max Activating Token Index: 715

Text #19

Max Range: 4.5713. Min Range: -4.5713

Max Act: 4.2126. Min Act: -0.1700

Data Index: 2158810 (Open Web Text)

Max Activating Token Index: 897