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

Dataset: Open Web Text

Neuron 573 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: 5.2873. Min Range: -5.2873

Max Act: 5.2873. Min Act: -0.1700

Data Index: 7646896 (Open Web Text)

Max Activating Token Index: 687

Text #1

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.2174. Min Act: -0.1700

Data Index: 5560237 (Open Web Text)

Max Activating Token Index: 640

Text #2

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.2230. Min Act: -0.1700

Data Index: 4844328 (Open Web Text)

Max Activating Token Index: 242

Text #3

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.1563. Min Act: -0.1700

Data Index: 7262057 (Open Web Text)

Max Activating Token Index: 561

Text #4

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0833. Min Act: -0.1700

Data Index: 1617 (Open Web Text)

Max Activating Token Index: 665

Text #5

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0680. Min Act: -0.1700

Data Index: 822576 (Open Web Text)

Max Activating Token Index: 874

Text #6

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.1014. Min Act: -0.1700

Data Index: 3953594 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0395. Min Act: -0.1700

Data Index: 1786950 (Open Web Text)

Max Activating Token Index: 297

Text #8

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0689. Min Act: -0.1700

Data Index: 2470691 (Open Web Text)

Max Activating Token Index: 876

Text #9

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0899. Min Act: -0.1700

Data Index: 8430992 (Open Web Text)

Max Activating Token Index: 996

Text #10

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0829. Min Act: -0.1700

Data Index: 8504646 (Open Web Text)

Max Activating Token Index: 306

Text #11

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0426. Min Act: -0.1700

Data Index: 2380981 (Open Web Text)

Max Activating Token Index: 127

Text #12

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0319. Min Act: -0.1700

Data Index: 5238314 (Open Web Text)

Max Activating Token Index: 1002

Text #13

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0441. Min Act: -0.1700

Data Index: 1667562 (Open Web Text)

Max Activating Token Index: 632

Text #14

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0429. Min Act: -0.1700

Data Index: 4756999 (Open Web Text)

Max Activating Token Index: 754

Text #15

Max Range: 5.2873. Min Range: -5.2873

Max Act: 4.9943. Min Act: -0.1700

Data Index: 6237083 (Open Web Text)

Max Activating Token Index: 678

Text #16

Max Range: 5.2873. Min Range: -5.2873

Max Act: 4.9994. Min Act: -0.1700

Data Index: 856084 (Open Web Text)

Max Activating Token Index: 920

Text #17

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0367. Min Act: -0.1700

Data Index: 1769193 (Open Web Text)

Max Activating Token Index: 978

Text #18

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0391. Min Act: -0.1699

Data Index: 5496466 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 5.2873. Min Range: -5.2873

Max Act: 5.0053. Min Act: -0.1700

Data Index: 2633352 (Open Web Text)

Max Activating Token Index: 711