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

Dataset: Open Web Text

Neuron 615 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: 3.4513. Min Range: -3.4513

Max Act: 3.4513. Min Act: -0.1700

Data Index: 8098990 (Open Web Text)

Max Activating Token Index: 285

Text #1

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.4504. Min Act: -0.1700

Data Index: 1582718 (Open Web Text)

Max Activating Token Index: 583

Text #2

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.4218. Min Act: -0.1700

Data Index: 8382726 (Open Web Text)

Max Activating Token Index: 889

Text #3

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3846. Min Act: -0.1700

Data Index: 3205827 (Open Web Text)

Max Activating Token Index: 185

Text #4

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3873. Min Act: -0.1700

Data Index: 3237506 (Open Web Text)

Max Activating Token Index: 532

Text #5

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3882. Min Act: -0.1700

Data Index: 6408953 (Open Web Text)

Max Activating Token Index: 771

Text #6

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3512. Min Act: -0.1700

Data Index: 8341176 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3784. Min Act: -0.1700

Data Index: 3205828 (Open Web Text)

Max Activating Token Index: 865

Text #8

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3643. Min Act: -0.1700

Data Index: 4539390 (Open Web Text)

Max Activating Token Index: 88

Text #9

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3798. Min Act: -0.1700

Data Index: 8699596 (Open Web Text)

Max Activating Token Index: 457

Text #10

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3742. Min Act: -0.1700

Data Index: 4155251 (Open Web Text)

Max Activating Token Index: 726

Text #11

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3722. Min Act: -0.1700

Data Index: 5144604 (Open Web Text)

Max Activating Token Index: 976

Text #12

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3636. Min Act: -0.1700

Data Index: 5509198 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3532. Min Act: -0.1700

Data Index: 5507318 (Open Web Text)

Max Activating Token Index: 751

Text #14

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3862. Min Act: -0.1700

Data Index: 8552478 (Open Web Text)

Max Activating Token Index: 563

Text #15

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3462. Min Act: -0.1700

Data Index: 2676905 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3365. Min Act: -0.1700

Data Index: 4465508 (Open Web Text)

Max Activating Token Index: 995

Text #17

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3271. Min Act: -0.1700

Data Index: 6492462 (Open Web Text)

Max Activating Token Index: 443

Text #18

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3705. Min Act: -0.1700

Data Index: 872191 (Open Web Text)

Max Activating Token Index: 814

Text #19

Max Range: 3.4513. Min Range: -3.4513

Max Act: 3.3458. Min Act: -0.1700

Data Index: 7081402 (Open Web Text)

Max Activating Token Index: 385