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

Dataset: Open Web Text

Neuron 520 in Layer 1

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: 3.3767. Min Range: -3.3767

Max Act: 3.3767. Min Act: -0.1700

Data Index: 684498 (Open Web Text)

Max Activating Token Index: 372

Text #1

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.3309. Min Act: -0.1700

Data Index: 8492049 (Open Web Text)

Max Activating Token Index: 312

Text #2

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.0431. Min Act: -0.1696

Data Index: 5013157 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 3.3767. Min Range: -3.3767

Max Act: 3.0120. Min Act: -0.1700

Data Index: 1373027 (Open Web Text)

Max Activating Token Index: 313

Text #4

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.9966. Min Act: -0.1700

Data Index: 5374938 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.9451. Min Act: -0.1700

Data Index: 5933374 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.9259. Min Act: -0.1700

Data Index: 3755972 (Open Web Text)

Max Activating Token Index: 412

Text #7

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.9123. Min Act: -0.1700

Data Index: 3596691 (Open Web Text)

Max Activating Token Index: 414

Text #8

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.9161. Min Act: -0.1700

Data Index: 6242696 (Open Web Text)

Max Activating Token Index: 426

Text #9

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.8689. Min Act: -0.1699

Data Index: 4520763 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.8729. Min Act: -0.1693

Data Index: 5013159 (Open Web Text)

Max Activating Token Index: 447

Text #11

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.8454. Min Act: -0.1700

Data Index: 655608 (Open Web Text)

Max Activating Token Index: 881

Text #12

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.8614. Min Act: -0.1700

Data Index: 5527237 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.8614. Min Act: -0.1700

Data Index: 5527241 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.8514. Min Act: -0.1700

Data Index: 8328925 (Open Web Text)

Max Activating Token Index: 189

Text #15

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.8390. Min Act: -0.1700

Data Index: 6287910 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.8439. Min Act: -0.1676

Data Index: 1081146 (Open Web Text)

Max Activating Token Index: 393

Text #17

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.8174. Min Act: -0.1700

Data Index: 6806403 (Open Web Text)

Max Activating Token Index: 268

Text #18

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.7977. Min Act: -0.1700

Data Index: 8155901 (Open Web Text)

Max Activating Token Index: 393

Text #19

Max Range: 3.3767. Min Range: -3.3767

Max Act: 2.8050. Min Act: -0.1700

Data Index: 3804229 (Open Web Text)

Max Activating Token Index: 411