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

Dataset: Open Web Text

Neuron 634 in Layer 4

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: 4.3253. Min Range: -4.3253

Max Act: 4.3024. Min Act: -0.1700

Data Index: 3793928 (Open Web Text)

Max Activating Token Index: 169

Text #1

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.3253. Min Act: -0.1700

Data Index: 1380888 (Open Web Text)

Max Activating Token Index: 1009

Text #2

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.3108. Min Act: -0.1700

Data Index: 7948357 (Open Web Text)

Max Activating Token Index: 452

Text #3

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.2571. Min Act: -0.1700

Data Index: 6039113 (Open Web Text)

Max Activating Token Index: 290

Text #4

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.2268. Min Act: -0.1700

Data Index: 4905337 (Open Web Text)

Max Activating Token Index: 200

Text #5

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.2876. Min Act: -0.1700

Data Index: 5255988 (Open Web Text)

Max Activating Token Index: 396

Text #6

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.2241. Min Act: -0.1700

Data Index: 1479937 (Open Web Text)

Max Activating Token Index: 837

Text #7

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.2293. Min Act: -0.1700

Data Index: 6739413 (Open Web Text)

Max Activating Token Index: 180

Text #8

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.2407. Min Act: -0.1700

Data Index: 198813 (Open Web Text)

Max Activating Token Index: 906

Text #9

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.2351. Min Act: -0.1700

Data Index: 5654632 (Open Web Text)

Max Activating Token Index: 445

Text #10

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.2381. Min Act: -0.1700

Data Index: 6983771 (Open Web Text)

Max Activating Token Index: 843

Text #11

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.2037. Min Act: -0.1700

Data Index: 3873879 (Open Web Text)

Max Activating Token Index: 1012

Text #12

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1879. Min Act: -0.1700

Data Index: 545582 (Open Web Text)

Max Activating Token Index: 971

Text #13

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.2373. Min Act: -0.1700

Data Index: 2219726 (Open Web Text)

Max Activating Token Index: 333

Text #14

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1991. Min Act: -0.1700

Data Index: 4099416 (Open Web Text)

Max Activating Token Index: 283

Text #15

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1758. Min Act: -0.1700

Data Index: 7311472 (Open Web Text)

Max Activating Token Index: 631

Text #16

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1753. Min Act: -0.1700

Data Index: 4600629 (Open Web Text)

Max Activating Token Index: 349

Text #17

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1098. Min Act: -0.1700

Data Index: 23569 (Open Web Text)

Max Activating Token Index: 91

Text #18

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1161. Min Act: -0.1700

Data Index: 7236295 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1134. Min Act: -0.1700

Data Index: 5418656 (Open Web Text)

Max Activating Token Index: 914