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

Dataset: Open Web Text

Neuron 2899 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: 7.3508. Min Range: -7.3508

Max Act: 7.3508. Min Act: -0.1700

Data Index: 2765243 (Open Web Text)

Max Activating Token Index: 606

Text #1

Max Range: 7.3508. Min Range: -7.3508

Max Act: 7.0968. Min Act: -0.1700

Data Index: 3528132 (Open Web Text)

Max Activating Token Index: 330

Text #2

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.9791. Min Act: -0.1700

Data Index: 4651425 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.7529. Min Act: -0.1700

Data Index: 5152853 (Open Web Text)

Max Activating Token Index: 661

Text #4

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.7861. Min Act: -0.1700

Data Index: 6058912 (Open Web Text)

Max Activating Token Index: 570

Text #5

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.7627. Min Act: -0.1700

Data Index: 3595972 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.7415. Min Act: -0.1700

Data Index: 749243 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.7223. Min Act: -0.1700

Data Index: 3668247 (Open Web Text)

Max Activating Token Index: 979

Text #8

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.6461. Min Act: -0.1700

Data Index: 3948909 (Open Web Text)

Max Activating Token Index: 439

Text #9

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.6413. Min Act: -0.1700

Data Index: 5201453 (Open Web Text)

Max Activating Token Index: 551

Text #10

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.5645. Min Act: -0.1700

Data Index: 2905697 (Open Web Text)

Max Activating Token Index: 931

Text #11

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.5907. Min Act: -0.1700

Data Index: 7155406 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.6412. Min Act: -0.1700

Data Index: 7854674 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.5586. Min Act: -0.1700

Data Index: 387495 (Open Web Text)

Max Activating Token Index: 318

Text #14

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.5684. Min Act: -0.1700

Data Index: 5925187 (Open Web Text)

Max Activating Token Index: 719

Text #15

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.5544. Min Act: -0.1700

Data Index: 163431 (Open Web Text)

Max Activating Token Index: 881

Text #16

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.5222. Min Act: -0.1700

Data Index: 8730726 (Open Web Text)

Max Activating Token Index: 301

Text #17

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.5294. Min Act: -0.1700

Data Index: 3891487 (Open Web Text)

Max Activating Token Index: 614

Text #18

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.4498. Min Act: -0.1700

Data Index: 3471699 (Open Web Text)

Max Activating Token Index: 579

Text #19

Max Range: 7.3508. Min Range: -7.3508

Max Act: 6.4265. Min Act: -0.1700

Data Index: 2494275 (Open Web Text)

Max Activating Token Index: 459