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

Dataset: Open Web Text

Neuron 1032 in Layer 2

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: 4.0580. Min Range: -4.0580

Max Act: 4.0580. Min Act: -0.1700

Data Index: 5873095 (Open Web Text)

Max Activating Token Index: 613

Text #1

Max Range: 4.0580. Min Range: -4.0580

Max Act: 4.0186. Min Act: -0.1700

Data Index: 3740253 (Open Web Text)

Max Activating Token Index: 246

Text #2

Max Range: 4.0580. Min Range: -4.0580

Max Act: 4.0475. Min Act: -0.1700

Data Index: 5682514 (Open Web Text)

Max Activating Token Index: 346

Text #3

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.9655. Min Act: -0.1700

Data Index: 7283332 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.9151. Min Act: -0.1700

Data Index: 6799926 (Open Web Text)

Max Activating Token Index: 212

Text #5

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.8666. Min Act: -0.1700

Data Index: 4940665 (Open Web Text)

Max Activating Token Index: 551

Text #6

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.8896. Min Act: -0.1700

Data Index: 991934 (Open Web Text)

Max Activating Token Index: 618

Text #7

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.8733. Min Act: -0.1700

Data Index: 1614868 (Open Web Text)

Max Activating Token Index: 638

Text #8

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.8342. Min Act: -0.1700

Data Index: 740132 (Open Web Text)

Max Activating Token Index: 876

Text #9

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.8543. Min Act: -0.1700

Data Index: 1324640 (Open Web Text)

Max Activating Token Index: 727

Text #10

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.8605. Min Act: -0.1700

Data Index: 4901528 (Open Web Text)

Max Activating Token Index: 83

Text #11

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.8226. Min Act: -0.1700

Data Index: 3826639 (Open Web Text)

Max Activating Token Index: 710

Text #12

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.7806. Min Act: -0.1700

Data Index: 432072 (Open Web Text)

Max Activating Token Index: 225

Text #13

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.7892. Min Act: -0.1700

Data Index: 1389354 (Open Web Text)

Max Activating Token Index: 312

Text #14

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.7529. Min Act: -0.1700

Data Index: 4351271 (Open Web Text)

Max Activating Token Index: 296

Text #15

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.7659. Min Act: -0.1700

Data Index: 325312 (Open Web Text)

Max Activating Token Index: 933

Text #16

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.7486. Min Act: -0.1700

Data Index: 2458992 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.7420. Min Act: -0.1700

Data Index: 4495341 (Open Web Text)

Max Activating Token Index: 512

Text #18

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.7606. Min Act: -0.1700

Data Index: 1171972 (Open Web Text)

Max Activating Token Index: 855

Text #19

Max Range: 4.0580. Min Range: -4.0580

Max Act: 3.7436. Min Act: -0.1700

Data Index: 1933913 (Open Web Text)

Max Activating Token Index: 903