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

Dataset: Open Web Text

Neuron 2271 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: 2.9355. Min Range: -2.9355

Max Act: 2.9355. Min Act: -0.1700

Data Index: 7035443 (Open Web Text)

Max Activating Token Index: 441

Text #1

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.8954. Min Act: -0.1700

Data Index: 7681080 (Open Web Text)

Max Activating Token Index: 669

Text #2

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.8878. Min Act: -0.1700

Data Index: 6949125 (Open Web Text)

Max Activating Token Index: 910

Text #3

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.8924. Min Act: -0.1700

Data Index: 5654715 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.8391. Min Act: -0.1700

Data Index: 1933451 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.8612. Min Act: -0.1700

Data Index: 6935131 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.8199. Min Act: -0.1700

Data Index: 4756479 (Open Web Text)

Max Activating Token Index: 134

Text #7

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7891. Min Act: -0.1700

Data Index: 342229 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7923. Min Act: -0.1700

Data Index: 7035453 (Open Web Text)

Max Activating Token Index: 245

Text #9

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7858. Min Act: -0.1700

Data Index: 7035445 (Open Web Text)

Max Activating Token Index: 587

Text #10

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7765. Min Act: -0.1700

Data Index: 7035454 (Open Web Text)

Max Activating Token Index: 281

Text #11

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7676. Min Act: -0.1700

Data Index: 5915500 (Open Web Text)

Max Activating Token Index: 460

Text #12

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7767. Min Act: -0.1700

Data Index: 8483057 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7611. Min Act: -0.1700

Data Index: 7035450 (Open Web Text)

Max Activating Token Index: 313

Text #14

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7572. Min Act: -0.1700

Data Index: 2682078 (Open Web Text)

Max Activating Token Index: 294

Text #15

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7470. Min Act: -0.1700

Data Index: 4868681 (Open Web Text)

Max Activating Token Index: 843

Text #16

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7137. Min Act: -0.1700

Data Index: 8319346 (Open Web Text)

Max Activating Token Index: 755

Text #17

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7507. Min Act: -0.1700

Data Index: 4692232 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7246. Min Act: -0.1700

Data Index: 7035452 (Open Web Text)

Max Activating Token Index: 313

Text #19

Max Range: 2.9355. Min Range: -2.9355

Max Act: 2.7254. Min Act: -0.1700

Data Index: 7091235 (Open Web Text)

Max Activating Token Index: 167