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

Dataset: Open Web Text

Neuron 2183 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: 3.4323. Min Range: -3.4323

Max Act: 3.4323. Min Act: -0.1700

Data Index: 504873 (Open Web Text)

Max Activating Token Index: 951

Text #1

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.4222. Min Act: -0.1700

Data Index: 2230341 (Open Web Text)

Max Activating Token Index: 472

Text #2

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.3776. Min Act: -0.1700

Data Index: 4941237 (Open Web Text)

Max Activating Token Index: 734

Text #3

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.3510. Min Act: -0.1700

Data Index: 703877 (Open Web Text)

Max Activating Token Index: 913

Text #4

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.3258. Min Act: -0.1700

Data Index: 418363 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.2792. Min Act: -0.1700

Data Index: 1310700 (Open Web Text)

Max Activating Token Index: 684

Text #6

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.2585. Min Act: -0.1700

Data Index: 7099322 (Open Web Text)

Max Activating Token Index: 345

Text #7

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.2535. Min Act: -0.1700

Data Index: 1219437 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.2801. Min Act: -0.1700

Data Index: 6126806 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.2548. Min Act: -0.1700

Data Index: 6977369 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.2707. Min Act: -0.1700

Data Index: 5537188 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.2387. Min Act: -0.1700

Data Index: 1041622 (Open Web Text)

Max Activating Token Index: 852

Text #12

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.2500. Min Act: -0.1700

Data Index: 7997405 (Open Web Text)

Max Activating Token Index: 224

Text #13

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.2073. Min Act: -0.1700

Data Index: 8761353 (Open Web Text)

Max Activating Token Index: 314

Text #14

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.1996. Min Act: -0.1700

Data Index: 1248385 (Open Web Text)

Max Activating Token Index: 1011

Text #15

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.1801. Min Act: -0.1700

Data Index: 6069922 (Open Web Text)

Max Activating Token Index: 547

Text #16

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.1775. Min Act: -0.1700

Data Index: 5144076 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.1887. Min Act: -0.1700

Data Index: 4644877 (Open Web Text)

Max Activating Token Index: 981

Text #18

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.1916. Min Act: -0.1700

Data Index: 7607192 (Open Web Text)

Max Activating Token Index: 323

Text #19

Max Range: 3.4323. Min Range: -3.4323

Max Act: 3.1293. Min Act: -0.1700

Data Index: 8104310 (Open Web Text)

Max Activating Token Index: 408