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

Dataset: Open Web Text

Neuron 1805 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: 5.2289. Min Range: -5.2289

Max Act: 5.2289. Min Act: -0.1700

Data Index: 2248262 (Open Web Text)

Max Activating Token Index: 178

Text #1

Max Range: 5.2289. Min Range: -5.2289

Max Act: 5.1788. Min Act: -0.1700

Data Index: 8415606 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 5.2289. Min Range: -5.2289

Max Act: 5.0764. Min Act: -0.1700

Data Index: 5896190 (Open Web Text)

Max Activating Token Index: 629

Text #3

Max Range: 5.2289. Min Range: -5.2289

Max Act: 5.0642. Min Act: -0.1700

Data Index: 5751492 (Open Web Text)

Max Activating Token Index: 640

Text #4

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9918. Min Act: -0.1700

Data Index: 2420910 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9810. Min Act: -0.1700

Data Index: 7443459 (Open Web Text)

Max Activating Token Index: 551

Text #6

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9761. Min Act: -0.1700

Data Index: 7007272 (Open Web Text)

Max Activating Token Index: 635

Text #7

Max Range: 5.2289. Min Range: -5.2289

Max Act: 5.0243. Min Act: -0.1700

Data Index: 6578281 (Open Web Text)

Max Activating Token Index: 245

Text #8

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9759. Min Act: -0.1700

Data Index: 8195101 (Open Web Text)

Max Activating Token Index: 673

Text #9

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9654. Min Act: -0.1700

Data Index: 2088100 (Open Web Text)

Max Activating Token Index: 632

Text #10

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9760. Min Act: -0.1700

Data Index: 1699920 (Open Web Text)

Max Activating Token Index: 915

Text #11

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9779. Min Act: -0.1700

Data Index: 7740092 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9764. Min Act: -0.1700

Data Index: 7208482 (Open Web Text)

Max Activating Token Index: 414

Text #13

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9721. Min Act: -0.1700

Data Index: 4242376 (Open Web Text)

Max Activating Token Index: 602

Text #14

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9751. Min Act: -0.1700

Data Index: 1135714 (Open Web Text)

Max Activating Token Index: 613

Text #15

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9721. Min Act: -0.1700

Data Index: 5897588 (Open Web Text)

Max Activating Token Index: 456

Text #16

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9256. Min Act: -0.1700

Data Index: 2679541 (Open Web Text)

Max Activating Token Index: 397

Text #17

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9351. Min Act: -0.1700

Data Index: 7155530 (Open Web Text)

Max Activating Token Index: 383

Text #18

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9223. Min Act: -0.1700

Data Index: 5214349 (Open Web Text)

Max Activating Token Index: 351

Text #19

Max Range: 5.2289. Min Range: -5.2289

Max Act: 4.9355. Min Act: -0.1700

Data Index: 29932 (Open Web Text)

Max Activating Token Index: 887