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

Dataset: Open Web Text

Neuron 3033 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: 3.3597. Min Range: -3.3597

Max Act: 3.3446. Min Act: -0.1700

Data Index: 8348019 (Open Web Text)

Max Activating Token Index: 115

Text #1

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.3597. Min Act: -0.1700

Data Index: 398213 (Open Web Text)

Max Activating Token Index: 155

Text #2

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.3027. Min Act: -0.1700

Data Index: 6134631 (Open Web Text)

Max Activating Token Index: 410

Text #3

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.2693. Min Act: -0.1700

Data Index: 3868570 (Open Web Text)

Max Activating Token Index: 265

Text #4

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.2412. Min Act: -0.1700

Data Index: 3946941 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.2544. Min Act: -0.1700

Data Index: 3654379 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.2021. Min Act: -0.1700

Data Index: 2394438 (Open Web Text)

Max Activating Token Index: 283

Text #7

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1963. Min Act: -0.1700

Data Index: 6742533 (Open Web Text)

Max Activating Token Index: 737

Text #8

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.2030. Min Act: -0.1700

Data Index: 3802413 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1804. Min Act: -0.1700

Data Index: 1450774 (Open Web Text)

Max Activating Token Index: 428

Text #10

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1951. Min Act: -0.1700

Data Index: 7157190 (Open Web Text)

Max Activating Token Index: 583

Text #11

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1756. Min Act: -0.1700

Data Index: 7385663 (Open Web Text)

Max Activating Token Index: 950

Text #12

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1591. Min Act: -0.1700

Data Index: 1955325 (Open Web Text)

Max Activating Token Index: 731

Text #13

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1620. Min Act: -0.1700

Data Index: 7317831 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1357. Min Act: -0.1700

Data Index: 3319894 (Open Web Text)

Max Activating Token Index: 837

Text #15

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1335. Min Act: -0.1700

Data Index: 7143885 (Open Web Text)

Max Activating Token Index: 523

Text #16

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1271. Min Act: -0.1700

Data Index: 3462298 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1201. Min Act: -0.1700

Data Index: 6034878 (Open Web Text)

Max Activating Token Index: 580

Text #18

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1304. Min Act: -0.1700

Data Index: 7905626 (Open Web Text)

Max Activating Token Index: 725

Text #19

Max Range: 3.3597. Min Range: -3.3597

Max Act: 3.1153. Min Act: -0.1700

Data Index: 6952587 (Open Web Text)

Max Activating Token Index: 493