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

Dataset: Open Web Text

Neuron 1617 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: 3.2367. Min Range: -3.2367

Max Act: 3.2367. Min Act: -0.1700

Data Index: 7086596 (Open Web Text)

Max Activating Token Index: 150

Text #1

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1497. Min Act: -0.1700

Data Index: 8826182 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1531. Min Act: -0.1700

Data Index: 5596129 (Open Web Text)

Max Activating Token Index: 100

Text #3

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1448. Min Act: -0.1700

Data Index: 8589228 (Open Web Text)

Max Activating Token Index: 735

Text #4

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0671. Min Act: -0.1700

Data Index: 848046 (Open Web Text)

Max Activating Token Index: 357

Text #5

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0591. Min Act: -0.1700

Data Index: 901590 (Open Web Text)

Max Activating Token Index: 732

Text #6

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0369. Min Act: -0.1700

Data Index: 8287453 (Open Web Text)

Max Activating Token Index: 941

Text #7

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0310. Min Act: -0.1700

Data Index: 7472322 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0077. Min Act: -0.1700

Data Index: 527661 (Open Web Text)

Max Activating Token Index: 854

Text #9

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9945. Min Act: -0.1700

Data Index: 4685060 (Open Web Text)

Max Activating Token Index: 129

Text #10

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9827. Min Act: -0.1700

Data Index: 8369115 (Open Web Text)

Max Activating Token Index: 433

Text #11

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9935. Min Act: -0.1700

Data Index: 5900762 (Open Web Text)

Max Activating Token Index: 913

Text #12

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9941. Min Act: -0.1700

Data Index: 5549540 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9765. Min Act: -0.1700

Data Index: 2905691 (Open Web Text)

Max Activating Token Index: 115

Text #14

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9656. Min Act: -0.1700

Data Index: 1459050 (Open Web Text)

Max Activating Token Index: 469

Text #15

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9641. Min Act: -0.1700

Data Index: 2127755 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9835. Min Act: -0.1700

Data Index: 5650784 (Open Web Text)

Max Activating Token Index: 555

Text #17

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9664. Min Act: -0.1700

Data Index: 2233346 (Open Web Text)

Max Activating Token Index: 43

Text #18

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9739. Min Act: -0.1700

Data Index: 3590829 (Open Web Text)

Max Activating Token Index: 882

Text #19

Max Range: 3.2367. Min Range: -3.2367

Max Act: 2.9528. Min Act: -0.1700

Data Index: 7567518 (Open Web Text)

Max Activating Token Index: 188