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

Dataset: Open Web Text

Neuron 2091 in Layer 6

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: 3.3178. Min Range: -3.3178

Max Act: 3.3144. Min Act: -0.1700

Data Index: 7779379 (Open Web Text)

Max Activating Token Index: 641

Text #1

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.3178. Min Act: -0.1700

Data Index: 195661 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.2944. Min Act: -0.1700

Data Index: 6896769 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.2514. Min Act: -0.1700

Data Index: 8203249 (Open Web Text)

Max Activating Token Index: 712

Text #4

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.2255. Min Act: -0.1700

Data Index: 200172 (Open Web Text)

Max Activating Token Index: 862

Text #5

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.1827. Min Act: -0.1700

Data Index: 4225593 (Open Web Text)

Max Activating Token Index: 359

Text #6

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.2044. Min Act: -0.1700

Data Index: 6555566 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.1855. Min Act: -0.1700

Data Index: 6896771 (Open Web Text)

Max Activating Token Index: 408

Text #8

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.1658. Min Act: -0.1700

Data Index: 8035574 (Open Web Text)

Max Activating Token Index: 667

Text #9

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.1411. Min Act: -0.1700

Data Index: 6416238 (Open Web Text)

Max Activating Token Index: 368

Text #10

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.1456. Min Act: -0.1700

Data Index: 2279832 (Open Web Text)

Max Activating Token Index: 377

Text #11

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.1267. Min Act: -0.1700

Data Index: 1348274 (Open Web Text)

Max Activating Token Index: 66

Text #12

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.1315. Min Act: -0.1700

Data Index: 7528723 (Open Web Text)

Max Activating Token Index: 58

Text #13

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.1088. Min Act: -0.1700

Data Index: 367428 (Open Web Text)

Max Activating Token Index: 704

Text #14

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.1001. Min Act: -0.1700

Data Index: 195502 (Open Web Text)

Max Activating Token Index: 352

Text #15

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.0898. Min Act: -0.1700

Data Index: 7679386 (Open Web Text)

Max Activating Token Index: 715

Text #16

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.0903. Min Act: -0.1700

Data Index: 6754462 (Open Web Text)

Max Activating Token Index: 478

Text #17

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.0664. Min Act: -0.1700

Data Index: 1512903 (Open Web Text)

Max Activating Token Index: 512

Text #18

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.0746. Min Act: -0.1700

Data Index: 6043957 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 3.3178. Min Range: -3.3178

Max Act: 3.0778. Min Act: -0.1700

Data Index: 6198502 (Open Web Text)

Max Activating Token Index: 789