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

Dataset: Open Web Text

Neuron 1996 in Layer 4

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: 3.8461. Min Range: -3.8461

Max Act: 3.8461. Min Act: -0.1700

Data Index: 4512626 (Open Web Text)

Max Activating Token Index: 595

Text #1

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.7010. Min Act: -0.1700

Data Index: 5962698 (Open Web Text)

Max Activating Token Index: 901

Text #2

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.6384. Min Act: -0.1700

Data Index: 4842213 (Open Web Text)

Max Activating Token Index: 124

Text #3

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.6825. Min Act: -0.1700

Data Index: 1788161 (Open Web Text)

Max Activating Token Index: 514

Text #4

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.6428. Min Act: -0.1700

Data Index: 4456398 (Open Web Text)

Max Activating Token Index: 875

Text #5

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.5539. Min Act: -0.1700

Data Index: 7189667 (Open Web Text)

Max Activating Token Index: 384

Text #6

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.5410. Min Act: -0.1700

Data Index: 3184123 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.5251. Min Act: -0.1700

Data Index: 5115017 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.5002. Min Act: -0.1700

Data Index: 3362154 (Open Web Text)

Max Activating Token Index: 389

Text #9

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4899. Min Act: -0.1700

Data Index: 1888582 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4992. Min Act: -0.1700

Data Index: 4854495 (Open Web Text)

Max Activating Token Index: 254

Text #11

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4949. Min Act: -0.1700

Data Index: 825793 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4734. Min Act: -0.1700

Data Index: 4705213 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4847. Min Act: -0.1700

Data Index: 7725340 (Open Web Text)

Max Activating Token Index: 628

Text #14

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4471. Min Act: -0.1700

Data Index: 4467604 (Open Web Text)

Max Activating Token Index: 874

Text #15

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4165. Min Act: -0.1700

Data Index: 5343088 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4400. Min Act: -0.1700

Data Index: 5609512 (Open Web Text)

Max Activating Token Index: 694

Text #17

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4621. Min Act: -0.1700

Data Index: 6326179 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4353. Min Act: -0.1700

Data Index: 7597684 (Open Web Text)

Max Activating Token Index: 790

Text #19

Max Range: 3.8461. Min Range: -3.8461

Max Act: 3.4266. Min Act: -0.1700

Data Index: 4346882 (Open Web Text)

Max Activating Token Index: 333