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

Dataset: Open Web Text

Neuron 1586 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: 3.0681. Min Range: -3.0681

Max Act: 3.0670. Min Act: -0.1700

Data Index: 2978670 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0681. Min Act: -0.1700

Data Index: 3750494 (Open Web Text)

Max Activating Token Index: 810

Text #2

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0325. Min Act: -0.1700

Data Index: 1558183 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 3.0681. Min Range: -3.0681

Max Act: 3.0200. Min Act: -0.1700

Data Index: 1789593 (Open Web Text)

Max Activating Token Index: 378

Text #4

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9971. Min Act: -0.1700

Data Index: 3967981 (Open Web Text)

Max Activating Token Index: 366

Text #5

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9909. Min Act: -0.1700

Data Index: 5133581 (Open Web Text)

Max Activating Token Index: 792

Text #6

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9945. Min Act: -0.1700

Data Index: 4455231 (Open Web Text)

Max Activating Token Index: 724

Text #7

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9787. Min Act: -0.1700

Data Index: 3597224 (Open Web Text)

Max Activating Token Index: 454

Text #8

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9829. Min Act: -0.1700

Data Index: 7501061 (Open Web Text)

Max Activating Token Index: 290

Text #9

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9808. Min Act: -0.1700

Data Index: 4244220 (Open Web Text)

Max Activating Token Index: 234

Text #10

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9751. Min Act: -0.1700

Data Index: 956005 (Open Web Text)

Max Activating Token Index: 457

Text #11

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9405. Min Act: -0.1700

Data Index: 4909985 (Open Web Text)

Max Activating Token Index: 848

Text #12

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9576. Min Act: -0.1700

Data Index: 489433 (Open Web Text)

Max Activating Token Index: 368

Text #13

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9243. Min Act: -0.1700

Data Index: 1693289 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9321. Min Act: -0.1700

Data Index: 4392443 (Open Web Text)

Max Activating Token Index: 863

Text #15

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.8957. Min Act: -0.1700

Data Index: 8303852 (Open Web Text)

Max Activating Token Index: 849

Text #16

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9169. Min Act: -0.1700

Data Index: 7496440 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9186. Min Act: -0.1700

Data Index: 4208220 (Open Web Text)

Max Activating Token Index: 747

Text #18

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.8929. Min Act: -0.1700

Data Index: 6656584 (Open Web Text)

Max Activating Token Index: 337

Text #19

Max Range: 3.0681. Min Range: -3.0681

Max Act: 2.9063. Min Act: -0.1700

Data Index: 6634445 (Open Web Text)

Max Activating Token Index: 403