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

Dataset: Open Web Text

Neuron 1576 in Layer 6

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: 3.5674. Min Range: -3.5674

Max Act: 3.5383. Min Act: -0.1700

Data Index: 3504298 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.5448. Min Act: -0.1700

Data Index: 8071326 (Open Web Text)

Max Activating Token Index: 218

Text #2

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.5674. Min Act: -0.1700

Data Index: 641328 (Open Web Text)

Max Activating Token Index: 492

Text #3

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4917. Min Act: -0.1700

Data Index: 3830323 (Open Web Text)

Max Activating Token Index: 948

Text #4

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.5000. Min Act: -0.1700

Data Index: 2264883 (Open Web Text)

Max Activating Token Index: 149

Text #5

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.5035. Min Act: -0.1700

Data Index: 5210223 (Open Web Text)

Max Activating Token Index: 120

Text #6

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.5071. Min Act: -0.1700

Data Index: 6560571 (Open Web Text)

Max Activating Token Index: 585

Text #7

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4723. Min Act: -0.1700

Data Index: 6091757 (Open Web Text)

Max Activating Token Index: 138

Text #8

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.5100. Min Act: -0.1700

Data Index: 1772737 (Open Web Text)

Max Activating Token Index: 911

Text #9

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4723. Min Act: -0.1700

Data Index: 1993776 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4715. Min Act: -0.1700

Data Index: 7082425 (Open Web Text)

Max Activating Token Index: 693

Text #11

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4863. Min Act: -0.1700

Data Index: 2838708 (Open Web Text)

Max Activating Token Index: 537

Text #12

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4723. Min Act: -0.1700

Data Index: 4089288 (Open Web Text)

Max Activating Token Index: 690

Text #13

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4536. Min Act: -0.1700

Data Index: 7334428 (Open Web Text)

Max Activating Token Index: 97

Text #14

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4492. Min Act: -0.1700

Data Index: 8198527 (Open Web Text)

Max Activating Token Index: 173

Text #15

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.5083. Min Act: -0.1700

Data Index: 3992569 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4399. Min Act: -0.1700

Data Index: 3650219 (Open Web Text)

Max Activating Token Index: 242

Text #17

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4198. Min Act: -0.1700

Data Index: 1379842 (Open Web Text)

Max Activating Token Index: 651

Text #18

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4690. Min Act: -0.1700

Data Index: 2095275 (Open Web Text)

Max Activating Token Index: 798

Text #19

Max Range: 3.5674. Min Range: -3.5674

Max Act: 3.4540. Min Act: -0.1700

Data Index: 6849272 (Open Web Text)

Max Activating Token Index: 469