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

Dataset: Open Web Text

Neuron 798 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: 1.4682. Min Range: -1.4682

Max Act: 1.4682. Min Act: -0.1700

Data Index: 8327435 (Open Web Text)

Max Activating Token Index: 224

Text #1

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4556. Min Act: -0.1673

Data Index: 4143790 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4582. Min Act: -0.1560

Data Index: 3259149 (Open Web Text)

Max Activating Token Index: 641

Text #3

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4471. Min Act: -0.1699

Data Index: 865100 (Open Web Text)

Max Activating Token Index: 337

Text #4

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4438. Min Act: -0.1699

Data Index: 1560725 (Open Web Text)

Max Activating Token Index: 1016

Text #5

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4390. Min Act: -0.1683

Data Index: 4643539 (Open Web Text)

Max Activating Token Index: 161

Text #6

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4268. Min Act: -0.1686

Data Index: 7948916 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4293. Min Act: -0.1700

Data Index: 3277758 (Open Web Text)

Max Activating Token Index: 105

Text #8

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4359. Min Act: -0.1695

Data Index: 5927283 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4183. Min Act: -0.1595

Data Index: 2619608 (Open Web Text)

Max Activating Token Index: 99

Text #10

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4250. Min Act: -0.1674

Data Index: 8341647 (Open Web Text)

Max Activating Token Index: 737

Text #11

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4296. Min Act: -0.1700

Data Index: 2872903 (Open Web Text)

Max Activating Token Index: 185

Text #12

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4311. Min Act: -0.1573

Data Index: 313312 (Open Web Text)

Max Activating Token Index: 242

Text #13

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4112. Min Act: -0.1700

Data Index: 3274291 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4213. Min Act: -0.1675

Data Index: 4847915 (Open Web Text)

Max Activating Token Index: 151

Text #15

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.3914. Min Act: -0.1570

Data Index: 2544296 (Open Web Text)

Max Activating Token Index: 736

Text #16

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4095. Min Act: -0.1670

Data Index: 914326 (Open Web Text)

Max Activating Token Index: 1002

Text #17

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4056. Min Act: -0.1700

Data Index: 2504964 (Open Web Text)

Max Activating Token Index: 101

Text #18

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.4032. Min Act: -0.1697

Data Index: 3927824 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 1.4682. Min Range: -1.4682

Max Act: 1.3954. Min Act: -0.1695

Data Index: 22791 (Open Web Text)

Max Activating Token Index: 502