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

Dataset: Open Web Text

Neuron 2017 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: 5.0588. Min Range: -5.0588

Max Act: 5.0588. Min Act: -0.1700

Data Index: 7241807 (Open Web Text)

Max Activating Token Index: 291

Text #1

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.9010. Min Act: -0.1700

Data Index: 2062423 (Open Web Text)

Max Activating Token Index: 941

Text #2

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8825. Min Act: -0.1700

Data Index: 7253318 (Open Web Text)

Max Activating Token Index: 160

Text #3

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.9002. Min Act: -0.1700

Data Index: 236472 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8545. Min Act: -0.1700

Data Index: 394025 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8288. Min Act: -0.1700

Data Index: 755718 (Open Web Text)

Max Activating Token Index: 700

Text #6

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8262. Min Act: -0.1700

Data Index: 4215910 (Open Web Text)

Max Activating Token Index: 984

Text #7

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8066. Min Act: -0.1700

Data Index: 1231113 (Open Web Text)

Max Activating Token Index: 702

Text #8

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8470. Min Act: -0.1700

Data Index: 125477 (Open Web Text)

Max Activating Token Index: 302

Text #9

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8224. Min Act: -0.1700

Data Index: 6994676 (Open Web Text)

Max Activating Token Index: 243

Text #10

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8023. Min Act: -0.1700

Data Index: 6577848 (Open Web Text)

Max Activating Token Index: 317

Text #11

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8269. Min Act: -0.1700

Data Index: 1264885 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.8044. Min Act: -0.1700

Data Index: 4962886 (Open Web Text)

Max Activating Token Index: 203

Text #13

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.7984. Min Act: -0.1700

Data Index: 2807605 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.7545. Min Act: -0.1700

Data Index: 5178246 (Open Web Text)

Max Activating Token Index: 807

Text #15

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.7309. Min Act: -0.1700

Data Index: 7103109 (Open Web Text)

Max Activating Token Index: 766

Text #16

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.7446. Min Act: -0.1700

Data Index: 6220483 (Open Web Text)

Max Activating Token Index: 729

Text #17

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.7659. Min Act: -0.1700

Data Index: 6297299 (Open Web Text)

Max Activating Token Index: 372

Text #18

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.7449. Min Act: -0.1700

Data Index: 7063692 (Open Web Text)

Max Activating Token Index: 884

Text #19

Max Range: 5.0588. Min Range: -5.0588

Max Act: 4.7319. Min Act: -0.1700

Data Index: 5995215 (Open Web Text)

Max Activating Token Index: 394