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

Dataset: Open Web Text

Neuron 528 in Layer 3

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: 1.9763. Min Range: -1.9763

Max Act: 1.9763. Min Act: -0.1700

Data Index: 6997413 (Open Web Text)

Max Activating Token Index: 771

Text #1

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8980. Min Act: -0.1700

Data Index: 7625742 (Open Web Text)

Max Activating Token Index: 348

Text #2

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8897. Min Act: -0.1700

Data Index: 1141450 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8552. Min Act: -0.1700

Data Index: 1108108 (Open Web Text)

Max Activating Token Index: 377

Text #4

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8379. Min Act: -0.1700

Data Index: 7841259 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8377. Min Act: -0.1700

Data Index: 2650043 (Open Web Text)

Max Activating Token Index: 830

Text #6

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8345. Min Act: -0.1700

Data Index: 5876106 (Open Web Text)

Max Activating Token Index: 819

Text #7

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8739. Min Act: -0.1700

Data Index: 6536684 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8099. Min Act: -0.1700

Data Index: 8798429 (Open Web Text)

Max Activating Token Index: 468

Text #9

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.7917. Min Act: -0.1700

Data Index: 7700791 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8770. Min Act: -0.1700

Data Index: 1196855 (Open Web Text)

Max Activating Token Index: 324

Text #11

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8265. Min Act: -0.1700

Data Index: 7043066 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8328. Min Act: -0.1700

Data Index: 447653 (Open Web Text)

Max Activating Token Index: 130

Text #13

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8347. Min Act: -0.1700

Data Index: 992873 (Open Web Text)

Max Activating Token Index: 600

Text #14

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8358. Min Act: -0.1700

Data Index: 77972 (Open Web Text)

Max Activating Token Index: 925

Text #15

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8066. Min Act: -0.1700

Data Index: 3865517 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8041. Min Act: -0.1700

Data Index: 1955712 (Open Web Text)

Max Activating Token Index: 643

Text #17

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.8099. Min Act: -0.1700

Data Index: 5336569 (Open Web Text)

Max Activating Token Index: 731

Text #18

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.7887. Min Act: -0.1700

Data Index: 3999458 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 1.9763. Min Range: -1.9763

Max Act: 1.7998. Min Act: -0.1700

Data Index: 832344 (Open Web Text)

Max Activating Token Index: 15