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

Dataset: Open Web Text

Neuron 28 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: 3.1834. Min Range: -3.1834

Max Act: 3.1834. Min Act: -0.1700

Data Index: 2080176 (Open Web Text)

Max Activating Token Index: 387

Text #1

Max Range: 3.1834. Min Range: -3.1834

Max Act: 3.1154. Min Act: -0.1700

Data Index: 4648682 (Open Web Text)

Max Activating Token Index: 91

Text #2

Max Range: 3.1834. Min Range: -3.1834

Max Act: 3.0492. Min Act: -0.1700

Data Index: 7362712 (Open Web Text)

Max Activating Token Index: 353

Text #3

Max Range: 3.1834. Min Range: -3.1834

Max Act: 3.0027. Min Act: -0.1700

Data Index: 4442928 (Open Web Text)

Max Activating Token Index: 313

Text #4

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.9918. Min Act: -0.1700

Data Index: 1070008 (Open Web Text)

Max Activating Token Index: 573

Text #5

Max Range: 3.1834. Min Range: -3.1834

Max Act: 3.0170. Min Act: -0.1700

Data Index: 3186300 (Open Web Text)

Max Activating Token Index: 681

Text #6

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.9733. Min Act: -0.1700

Data Index: 1137685 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.9535. Min Act: -0.1700

Data Index: 7069028 (Open Web Text)

Max Activating Token Index: 703

Text #8

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.9761. Min Act: -0.1700

Data Index: 5960573 (Open Web Text)

Max Activating Token Index: 617

Text #9

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.9182. Min Act: -0.1700

Data Index: 4633818 (Open Web Text)

Max Activating Token Index: 554

Text #10

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.9419. Min Act: -0.1700

Data Index: 6003498 (Open Web Text)

Max Activating Token Index: 163

Text #11

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.8885. Min Act: -0.1700

Data Index: 6814788 (Open Web Text)

Max Activating Token Index: 252

Text #12

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.9402. Min Act: -0.1700

Data Index: 4976920 (Open Web Text)

Max Activating Token Index: 327

Text #13

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.9211. Min Act: -0.1700

Data Index: 1330716 (Open Web Text)

Max Activating Token Index: 472

Text #14

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.8909. Min Act: -0.1700

Data Index: 7809835 (Open Web Text)

Max Activating Token Index: 784

Text #15

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.8644. Min Act: -0.1700

Data Index: 1004928 (Open Web Text)

Max Activating Token Index: 477

Text #16

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.8813. Min Act: -0.1700

Data Index: 8034474 (Open Web Text)

Max Activating Token Index: 418

Text #17

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.8526. Min Act: -0.1700

Data Index: 6405720 (Open Web Text)

Max Activating Token Index: 627

Text #18

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.8823. Min Act: -0.1700

Data Index: 453610 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 3.1834. Min Range: -3.1834

Max Act: 2.8542. Min Act: -0.1700

Data Index: 2914682 (Open Web Text)

Max Activating Token Index: 478