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

Dataset: Open Web Text

Neuron 1327 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: 4.4369. Min Range: -4.4369

Max Act: 4.4226. Min Act: -0.1700

Data Index: 3245493 (Open Web Text)

Max Activating Token Index: 884

Text #1

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.4369. Min Act: -0.1700

Data Index: 5821173 (Open Web Text)

Max Activating Token Index: 625

Text #2

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.2556. Min Act: -0.1700

Data Index: 6785965 (Open Web Text)

Max Activating Token Index: 644

Text #3

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.1946. Min Act: -0.1700

Data Index: 8703552 (Open Web Text)

Max Activating Token Index: 256

Text #4

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.1169. Min Act: -0.1700

Data Index: 1743123 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.1128. Min Act: -0.1700

Data Index: 2476885 (Open Web Text)

Max Activating Token Index: 505

Text #6

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.0493. Min Act: -0.1700

Data Index: 3310428 (Open Web Text)

Max Activating Token Index: 403

Text #7

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.0429. Min Act: -0.1700

Data Index: 3337530 (Open Web Text)

Max Activating Token Index: 968

Text #8

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.0666. Min Act: -0.1700

Data Index: 5563107 (Open Web Text)

Max Activating Token Index: 839

Text #9

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.0652. Min Act: -0.1700

Data Index: 4320536 (Open Web Text)

Max Activating Token Index: 754

Text #10

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.0021. Min Act: -0.1700

Data Index: 5045564 (Open Web Text)

Max Activating Token Index: 331

Text #11

Max Range: 4.4369. Min Range: -4.4369

Max Act: 3.8906. Min Act: -0.1700

Data Index: 4329771 (Open Web Text)

Max Activating Token Index: 837

Text #12

Max Range: 4.4369. Min Range: -4.4369

Max Act: 3.9774. Min Act: -0.1700

Data Index: 4307652 (Open Web Text)

Max Activating Token Index: 549

Text #13

Max Range: 4.4369. Min Range: -4.4369

Max Act: 4.0001. Min Act: -0.1700

Data Index: 694702 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 4.4369. Min Range: -4.4369

Max Act: 3.9183. Min Act: -0.1700

Data Index: 1852308 (Open Web Text)

Max Activating Token Index: 412

Text #15

Max Range: 4.4369. Min Range: -4.4369

Max Act: 3.9422. Min Act: -0.1700

Data Index: 5816595 (Open Web Text)

Max Activating Token Index: 315

Text #16

Max Range: 4.4369. Min Range: -4.4369

Max Act: 3.9757. Min Act: -0.1699

Data Index: 1534838 (Open Web Text)

Max Activating Token Index: 699

Text #17

Max Range: 4.4369. Min Range: -4.4369

Max Act: 3.8915. Min Act: -0.1700

Data Index: 3380733 (Open Web Text)

Max Activating Token Index: 222

Text #18

Max Range: 4.4369. Min Range: -4.4369

Max Act: 3.9226. Min Act: -0.1700

Data Index: 4837645 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 4.4369. Min Range: -4.4369

Max Act: 3.8826. Min Act: -0.1700

Data Index: 5889279 (Open Web Text)

Max Activating Token Index: 368