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

Dataset: Open Web Text

Neuron 2309 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: 4.2323. Min Range: -4.2323

Max Act: 4.2323. Min Act: -0.1700

Data Index: 6219962 (Open Web Text)

Max Activating Token Index: 386

Text #1

Max Range: 4.2323. Min Range: -4.2323

Max Act: 4.2216. Min Act: -0.1700

Data Index: 300944 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 4.2323. Min Range: -4.2323

Max Act: 4.1528. Min Act: -0.1700

Data Index: 5938436 (Open Web Text)

Max Activating Token Index: 589

Text #3

Max Range: 4.2323. Min Range: -4.2323

Max Act: 4.1227. Min Act: -0.1700

Data Index: 45082 (Open Web Text)

Max Activating Token Index: 311

Text #4

Max Range: 4.2323. Min Range: -4.2323

Max Act: 4.1868. Min Act: -0.1700

Data Index: 8107642 (Open Web Text)

Max Activating Token Index: 550

Text #5

Max Range: 4.2323. Min Range: -4.2323

Max Act: 4.0878. Min Act: -0.1700

Data Index: 5855485 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 4.2323. Min Range: -4.2323

Max Act: 4.0753. Min Act: -0.1700

Data Index: 3554538 (Open Web Text)

Max Activating Token Index: 364

Text #7

Max Range: 4.2323. Min Range: -4.2323

Max Act: 4.1327. Min Act: -0.1700

Data Index: 5748413 (Open Web Text)

Max Activating Token Index: 382

Text #8

Max Range: 4.2323. Min Range: -4.2323

Max Act: 4.0728. Min Act: -0.1700

Data Index: 5027151 (Open Web Text)

Max Activating Token Index: 571

Text #9

Max Range: 4.2323. Min Range: -4.2323

Max Act: 4.0686. Min Act: -0.1700

Data Index: 3398538 (Open Web Text)

Max Activating Token Index: 47

Text #10

Max Range: 4.2323. Min Range: -4.2323

Max Act: 3.9979. Min Act: -0.1700

Data Index: 2143346 (Open Web Text)

Max Activating Token Index: 369

Text #11

Max Range: 4.2323. Min Range: -4.2323

Max Act: 3.9856. Min Act: -0.1700

Data Index: 2146108 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 4.2323. Min Range: -4.2323

Max Act: 3.9958. Min Act: -0.1700

Data Index: 4023189 (Open Web Text)

Max Activating Token Index: 119

Text #13

Max Range: 4.2323. Min Range: -4.2323

Max Act: 3.9987. Min Act: -0.1700

Data Index: 385410 (Open Web Text)

Max Activating Token Index: 774

Text #14

Max Range: 4.2323. Min Range: -4.2323

Max Act: 3.9789. Min Act: -0.1700

Data Index: 2174959 (Open Web Text)

Max Activating Token Index: 600

Text #15

Max Range: 4.2323. Min Range: -4.2323

Max Act: 3.9783. Min Act: -0.1700

Data Index: 1847428 (Open Web Text)

Max Activating Token Index: 216

Text #16

Max Range: 4.2323. Min Range: -4.2323

Max Act: 3.9602. Min Act: -0.1700

Data Index: 8045771 (Open Web Text)

Max Activating Token Index: 239

Text #17

Max Range: 4.2323. Min Range: -4.2323

Max Act: 3.9414. Min Act: -0.1700

Data Index: 2252314 (Open Web Text)

Max Activating Token Index: 745

Text #18

Max Range: 4.2323. Min Range: -4.2323

Max Act: 3.9257. Min Act: -0.1700

Data Index: 3815480 (Open Web Text)

Max Activating Token Index: 654

Text #19

Max Range: 4.2323. Min Range: -4.2323

Max Act: 3.9457. Min Act: -0.1700

Data Index: 4634291 (Open Web Text)

Max Activating Token Index: 308