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

Dataset: Open Web Text

Neuron 2039 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: 4.2159. Min Range: -4.2159

Max Act: 4.2159. Min Act: -0.1700

Data Index: 6728729 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1872. Min Act: -0.1700

Data Index: 5278921 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1760. Min Act: -0.1700

Data Index: 1744211 (Open Web Text)

Max Activating Token Index: 1015

Text #3

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1689. Min Act: -0.1700

Data Index: 5072328 (Open Web Text)

Max Activating Token Index: 859

Text #4

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1403. Min Act: -0.1700

Data Index: 5101481 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1267. Min Act: -0.1700

Data Index: 90332 (Open Web Text)

Max Activating Token Index: 359

Text #6

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1111. Min Act: -0.1700

Data Index: 8361537 (Open Web Text)

Max Activating Token Index: 750

Text #7

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1011. Min Act: -0.1700

Data Index: 2410182 (Open Web Text)

Max Activating Token Index: 640

Text #8

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0969. Min Act: -0.1700

Data Index: 737821 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0663. Min Act: -0.1700

Data Index: 1830348 (Open Web Text)

Max Activating Token Index: 525

Text #10

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0765. Min Act: -0.1700

Data Index: 4053189 (Open Web Text)

Max Activating Token Index: 327

Text #11

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0599. Min Act: -0.1700

Data Index: 4836355 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0667. Min Act: -0.1700

Data Index: 6908741 (Open Web Text)

Max Activating Token Index: 613

Text #13

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0786. Min Act: -0.1700

Data Index: 3183197 (Open Web Text)

Max Activating Token Index: 389

Text #14

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0313. Min Act: -0.1700

Data Index: 5116725 (Open Web Text)

Max Activating Token Index: 375

Text #15

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0380. Min Act: -0.1700

Data Index: 7180769 (Open Web Text)

Max Activating Token Index: 684

Text #16

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0291. Min Act: -0.1700

Data Index: 434458 (Open Web Text)

Max Activating Token Index: 420

Text #17

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0310. Min Act: -0.1700

Data Index: 3834887 (Open Web Text)

Max Activating Token Index: 978

Text #18

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0428. Min Act: -0.1700

Data Index: 5632169 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0263. Min Act: -0.1700

Data Index: 7586818 (Open Web Text)

Max Activating Token Index: 325