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

Dataset: Open Web Text

Neuron 2788 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: 5.2725. Min Range: -5.2725

Max Act: 5.2725. Min Act: -0.1700

Data Index: 7472109 (Open Web Text)

Max Activating Token Index: 736

Text #1

Max Range: 5.2725. Min Range: -5.2725

Max Act: 5.0898. Min Act: -0.1700

Data Index: 2221255 (Open Web Text)

Max Activating Token Index: 607

Text #2

Max Range: 5.2725. Min Range: -5.2725

Max Act: 5.0302. Min Act: -0.1700

Data Index: 5423475 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.8162. Min Act: -0.1700

Data Index: 4902161 (Open Web Text)

Max Activating Token Index: 433

Text #4

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.8293. Min Act: -0.1700

Data Index: 2544507 (Open Web Text)

Max Activating Token Index: 727

Text #5

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.8126. Min Act: -0.1700

Data Index: 3636224 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7155. Min Act: -0.1700

Data Index: 491151 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7393. Min Act: -0.1700

Data Index: 5745992 (Open Web Text)

Max Activating Token Index: 439

Text #8

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7134. Min Act: -0.1700

Data Index: 4581121 (Open Web Text)

Max Activating Token Index: 172

Text #9

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7015. Min Act: -0.1700

Data Index: 6428068 (Open Web Text)

Max Activating Token Index: 271

Text #10

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.7151. Min Act: -0.1700

Data Index: 308504 (Open Web Text)

Max Activating Token Index: 783

Text #11

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6688. Min Act: -0.1700

Data Index: 1530305 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6406. Min Act: -0.1700

Data Index: 2358362 (Open Web Text)

Max Activating Token Index: 654

Text #13

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6732. Min Act: -0.1700

Data Index: 330341 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6359. Min Act: -0.1700

Data Index: 6940077 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.6154. Min Act: -0.1700

Data Index: 6094320 (Open Web Text)

Max Activating Token Index: 1004

Text #16

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.5983. Min Act: -0.1700

Data Index: 806343 (Open Web Text)

Max Activating Token Index: 160

Text #17

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.5930. Min Act: -0.1700

Data Index: 2405416 (Open Web Text)

Max Activating Token Index: 88

Text #18

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.5509. Min Act: -0.1700

Data Index: 5102532 (Open Web Text)

Max Activating Token Index: 592

Text #19

Max Range: 5.2725. Min Range: -5.2725

Max Act: 4.5764. Min Act: -0.1700

Data Index: 5394955 (Open Web Text)

Max Activating Token Index: 388