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

Dataset: Open Web Text

Neuron 662 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: 4.2973. Min Range: -4.2973

Max Act: 4.2791. Min Act: -0.1700

Data Index: 6966935 (Open Web Text)

Max Activating Token Index: 685

Text #1

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.2973. Min Act: -0.1700

Data Index: 472183 (Open Web Text)

Max Activating Token Index: 823

Text #2

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.2863. Min Act: -0.1700

Data Index: 513776 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.1746. Min Act: -0.1700

Data Index: 7728397 (Open Web Text)

Max Activating Token Index: 715

Text #4

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0971. Min Act: -0.1700

Data Index: 8033552 (Open Web Text)

Max Activating Token Index: 596

Text #5

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0948. Min Act: -0.1700

Data Index: 938806 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0968. Min Act: -0.1700

Data Index: 7797022 (Open Web Text)

Max Activating Token Index: 227

Text #7

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0688. Min Act: -0.1700

Data Index: 2551540 (Open Web Text)

Max Activating Token Index: 646

Text #8

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0800. Min Act: -0.1700

Data Index: 5196441 (Open Web Text)

Max Activating Token Index: 202

Text #9

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0394. Min Act: -0.1700

Data Index: 4545973 (Open Web Text)

Max Activating Token Index: 541

Text #10

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0480. Min Act: -0.1700

Data Index: 5331955 (Open Web Text)

Max Activating Token Index: 958

Text #11

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0251. Min Act: -0.1700

Data Index: 4748431 (Open Web Text)

Max Activating Token Index: 465

Text #12

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0466. Min Act: -0.1700

Data Index: 1774441 (Open Web Text)

Max Activating Token Index: 219

Text #13

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0557. Min Act: -0.1700

Data Index: 1530128 (Open Web Text)

Max Activating Token Index: 760

Text #14

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0779. Min Act: -0.1700

Data Index: 500909 (Open Web Text)

Max Activating Token Index: 761

Text #15

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0412. Min Act: -0.1700

Data Index: 2646576 (Open Web Text)

Max Activating Token Index: 106

Text #16

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0041. Min Act: -0.1700

Data Index: 7728399 (Open Web Text)

Max Activating Token Index: 601

Text #17

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0114. Min Act: -0.1700

Data Index: 4987944 (Open Web Text)

Max Activating Token Index: 283

Text #18

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0256. Min Act: -0.1700

Data Index: 150909 (Open Web Text)

Max Activating Token Index: 724

Text #19

Max Range: 4.2973. Min Range: -4.2973

Max Act: 4.0453. Min Act: -0.1700

Data Index: 27825 (Open Web Text)

Max Activating Token Index: 126