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

Dataset: Open Web Text

Neuron 2832 in Layer 5

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: 5.4569. Min Range: -5.4569

Max Act: 5.4569. Min Act: -0.1700

Data Index: 7537595 (Open Web Text)

Max Activating Token Index: 238

Text #1

Max Range: 5.4569. Min Range: -5.4569

Max Act: 5.1717. Min Act: -0.1700

Data Index: 5794492 (Open Web Text)

Max Activating Token Index: 671

Text #2

Max Range: 5.4569. Min Range: -5.4569

Max Act: 5.1652. Min Act: -0.1700

Data Index: 3774545 (Open Web Text)

Max Activating Token Index: 452

Text #3

Max Range: 5.4569. Min Range: -5.4569

Max Act: 5.1655. Min Act: -0.1700

Data Index: 2838769 (Open Web Text)

Max Activating Token Index: 837

Text #4

Max Range: 5.4569. Min Range: -5.4569

Max Act: 5.1595. Min Act: -0.1700

Data Index: 5692073 (Open Web Text)

Max Activating Token Index: 313

Text #5

Max Range: 5.4569. Min Range: -5.4569

Max Act: 5.1233. Min Act: -0.1700

Data Index: 8826483 (Open Web Text)

Max Activating Token Index: 866

Text #6

Max Range: 5.4569. Min Range: -5.4569

Max Act: 5.0664. Min Act: -0.1700

Data Index: 7618834 (Open Web Text)

Max Activating Token Index: 483

Text #7

Max Range: 5.4569. Min Range: -5.4569

Max Act: 5.1354. Min Act: -0.1700

Data Index: 276391 (Open Web Text)

Max Activating Token Index: 662

Text #8

Max Range: 5.4569. Min Range: -5.4569

Max Act: 5.0952. Min Act: -0.1700

Data Index: 3977771 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 5.4569. Min Range: -5.4569

Max Act: 5.0472. Min Act: -0.1700

Data Index: 2901446 (Open Web Text)

Max Activating Token Index: 790

Text #10

Max Range: 5.4569. Min Range: -5.4569

Max Act: 4.9894. Min Act: -0.1700

Data Index: 6154420 (Open Web Text)

Max Activating Token Index: 463

Text #11

Max Range: 5.4569. Min Range: -5.4569

Max Act: 4.9805. Min Act: -0.1700

Data Index: 7916205 (Open Web Text)

Max Activating Token Index: 643

Text #12

Max Range: 5.4569. Min Range: -5.4569

Max Act: 4.9707. Min Act: -0.1700

Data Index: 1708548 (Open Web Text)

Max Activating Token Index: 982

Text #13

Max Range: 5.4569. Min Range: -5.4569

Max Act: 4.9350. Min Act: -0.1700

Data Index: 6989932 (Open Web Text)

Max Activating Token Index: 929

Text #14

Max Range: 5.4569. Min Range: -5.4569

Max Act: 4.9370. Min Act: -0.1700

Data Index: 3869712 (Open Web Text)

Max Activating Token Index: 244

Text #15

Max Range: 5.4569. Min Range: -5.4569

Max Act: 4.9073. Min Act: -0.1700

Data Index: 2184503 (Open Web Text)

Max Activating Token Index: 257

Text #16

Max Range: 5.4569. Min Range: -5.4569

Max Act: 4.9103. Min Act: -0.1700

Data Index: 8418233 (Open Web Text)

Max Activating Token Index: 939

Text #17

Max Range: 5.4569. Min Range: -5.4569

Max Act: 4.9355. Min Act: -0.1700

Data Index: 6048800 (Open Web Text)

Max Activating Token Index: 964

Text #18

Max Range: 5.4569. Min Range: -5.4569

Max Act: 4.9070. Min Act: -0.1700

Data Index: 6440925 (Open Web Text)

Max Activating Token Index: 221

Text #19

Max Range: 5.4569. Min Range: -5.4569

Max Act: 4.8746. Min Act: -0.1700

Data Index: 6236830 (Open Web Text)

Max Activating Token Index: 602