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

Dataset: Open Web Text

Neuron 2513 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: 4.7604. Min Range: -4.7604

Max Act: 4.7604. Min Act: -0.1700

Data Index: 1044167 (Open Web Text)

Max Activating Token Index: 311

Text #1

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.7587. Min Act: -0.1700

Data Index: 7526518 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.7546. Min Act: -0.1700

Data Index: 5436466 (Open Web Text)

Max Activating Token Index: 819

Text #3

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.6763. Min Act: -0.1700

Data Index: 2579400 (Open Web Text)

Max Activating Token Index: 276

Text #4

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.6537. Min Act: -0.1700

Data Index: 5467780 (Open Web Text)

Max Activating Token Index: 769

Text #5

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.6591. Min Act: -0.1700

Data Index: 7980263 (Open Web Text)

Max Activating Token Index: 720

Text #6

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.6338. Min Act: -0.1700

Data Index: 786602 (Open Web Text)

Max Activating Token Index: 191

Text #7

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.6147. Min Act: -0.1700

Data Index: 4798778 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.6454. Min Act: -0.1700

Data Index: 6210100 (Open Web Text)

Max Activating Token Index: 229

Text #9

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5727. Min Act: -0.1700

Data Index: 3360855 (Open Web Text)

Max Activating Token Index: 63

Text #10

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5726. Min Act: -0.1700

Data Index: 5383074 (Open Web Text)

Max Activating Token Index: 369

Text #11

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5956. Min Act: -0.1700

Data Index: 3743362 (Open Web Text)

Max Activating Token Index: 505

Text #12

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5769. Min Act: -0.1700

Data Index: 6236809 (Open Web Text)

Max Activating Token Index: 368

Text #13

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5554. Min Act: -0.1700

Data Index: 7698974 (Open Web Text)

Max Activating Token Index: 913

Text #14

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5592. Min Act: -0.1700

Data Index: 5357558 (Open Web Text)

Max Activating Token Index: 67

Text #15

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5699. Min Act: -0.1700

Data Index: 4547387 (Open Web Text)

Max Activating Token Index: 872

Text #16

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5595. Min Act: -0.1700

Data Index: 422561 (Open Web Text)

Max Activating Token Index: 538

Text #17

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5244. Min Act: -0.1700

Data Index: 492754 (Open Web Text)

Max Activating Token Index: 530

Text #18

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5251. Min Act: -0.1700

Data Index: 2910355 (Open Web Text)

Max Activating Token Index: 206

Text #19

Max Range: 4.7604. Min Range: -4.7604

Max Act: 4.5230. Min Act: -0.1700

Data Index: 3166248 (Open Web Text)

Max Activating Token Index: 214