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

Dataset: Open Web Text

Neuron 431 in Layer 3

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: 3.7783. Min Range: -3.7783

Max Act: 3.7783. Min Act: -0.1700

Data Index: 1169867 (Open Web Text)

Max Activating Token Index: 266

Text #1

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6656. Min Act: -0.1700

Data Index: 570470 (Open Web Text)

Max Activating Token Index: 918

Text #2

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6463. Min Act: -0.1700

Data Index: 1134181 (Open Web Text)

Max Activating Token Index: 555

Text #3

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6138. Min Act: -0.1700

Data Index: 8299610 (Open Web Text)

Max Activating Token Index: 639

Text #4

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.6243. Min Act: -0.1700

Data Index: 1244057 (Open Web Text)

Max Activating Token Index: 361

Text #5

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5636. Min Act: -0.1700

Data Index: 561329 (Open Web Text)

Max Activating Token Index: 874

Text #6

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5538. Min Act: -0.1700

Data Index: 4186759 (Open Web Text)

Max Activating Token Index: 243

Text #7

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5464. Min Act: -0.1700

Data Index: 7454419 (Open Web Text)

Max Activating Token Index: 161

Text #8

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.4962. Min Act: -0.1700

Data Index: 241312 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5223. Min Act: -0.1700

Data Index: 7904050 (Open Web Text)

Max Activating Token Index: 911

Text #10

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5656. Min Act: -0.1700

Data Index: 6395622 (Open Web Text)

Max Activating Token Index: 829

Text #11

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.4982. Min Act: -0.1700

Data Index: 760341 (Open Web Text)

Max Activating Token Index: 768

Text #12

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5327. Min Act: -0.1700

Data Index: 1103665 (Open Web Text)

Max Activating Token Index: 789

Text #13

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.4898. Min Act: -0.1700

Data Index: 5204180 (Open Web Text)

Max Activating Token Index: 737

Text #14

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.4831. Min Act: -0.1700

Data Index: 2364091 (Open Web Text)

Max Activating Token Index: 800

Text #15

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5090. Min Act: -0.1700

Data Index: 4282573 (Open Web Text)

Max Activating Token Index: 563

Text #16

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.4978. Min Act: -0.1700

Data Index: 4261232 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.4891. Min Act: -0.1700

Data Index: 5639463 (Open Web Text)

Max Activating Token Index: 937

Text #18

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.4806. Min Act: -0.1700

Data Index: 4916 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 3.7783. Min Range: -3.7783

Max Act: 3.5058. Min Act: -0.1700

Data Index: 4613530 (Open Web Text)

Max Activating Token Index: 602