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

Dataset: Open Web Text

Neuron 737 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: 4.0200. Min Range: -4.0200

Max Act: 4.0200. Min Act: -0.1700

Data Index: 6659561 (Open Web Text)

Max Activating Token Index: 723

Text #1

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.9168. Min Act: -0.1700

Data Index: 3537910 (Open Web Text)

Max Activating Token Index: 911

Text #2

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8951. Min Act: -0.1700

Data Index: 7161063 (Open Web Text)

Max Activating Token Index: 227

Text #3

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.9259. Min Act: -0.1700

Data Index: 3698166 (Open Web Text)

Max Activating Token Index: 455

Text #4

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8911. Min Act: -0.1700

Data Index: 5294433 (Open Web Text)

Max Activating Token Index: 515

Text #5

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8876. Min Act: -0.1700

Data Index: 7065485 (Open Web Text)

Max Activating Token Index: 704

Text #6

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8810. Min Act: -0.1700

Data Index: 8577826 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8602. Min Act: -0.1700

Data Index: 1128418 (Open Web Text)

Max Activating Token Index: 365

Text #8

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8670. Min Act: -0.1700

Data Index: 51035 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8547. Min Act: -0.1700

Data Index: 4565364 (Open Web Text)

Max Activating Token Index: 437

Text #10

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8662. Min Act: -0.1700

Data Index: 4673373 (Open Web Text)

Max Activating Token Index: 933

Text #11

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8607. Min Act: -0.1700

Data Index: 6201780 (Open Web Text)

Max Activating Token Index: 409

Text #12

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8475. Min Act: -0.1700

Data Index: 4400292 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8188. Min Act: -0.1700

Data Index: 1843024 (Open Web Text)

Max Activating Token Index: 262

Text #14

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8072. Min Act: -0.1700

Data Index: 4469123 (Open Web Text)

Max Activating Token Index: 450

Text #15

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8516. Min Act: -0.1700

Data Index: 1989458 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8283. Min Act: -0.1700

Data Index: 5348528 (Open Web Text)

Max Activating Token Index: 454

Text #17

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8140. Min Act: -0.1700

Data Index: 2982247 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8183. Min Act: -0.1700

Data Index: 4063525 (Open Web Text)

Max Activating Token Index: 327

Text #19

Max Range: 4.0200. Min Range: -4.0200

Max Act: 3.8691. Min Act: -0.1700

Data Index: 2978541 (Open Web Text)

Max Activating Token Index: 721