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

Dataset: Open Web Text

Neuron 1638 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: 3.0973. Min Range: -3.0973

Max Act: 3.0973. Min Act: -0.1700

Data Index: 7453318 (Open Web Text)

Max Activating Token Index: 1018

Text #1

Max Range: 3.0973. Min Range: -3.0973

Max Act: 3.0963. Min Act: -0.1700

Data Index: 8338479 (Open Web Text)

Max Activating Token Index: 104

Text #2

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9916. Min Act: -0.1700

Data Index: 4319062 (Open Web Text)

Max Activating Token Index: 995

Text #3

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9816. Min Act: -0.1700

Data Index: 3805537 (Open Web Text)

Max Activating Token Index: 564

Text #4

Max Range: 3.0973. Min Range: -3.0973

Max Act: 3.0191. Min Act: -0.1700

Data Index: 4975130 (Open Web Text)

Max Activating Token Index: 420

Text #5

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9911. Min Act: -0.1700

Data Index: 136354 (Open Web Text)

Max Activating Token Index: 899

Text #6

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9812. Min Act: -0.1700

Data Index: 8262627 (Open Web Text)

Max Activating Token Index: 468

Text #7

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9746. Min Act: -0.1700

Data Index: 2865869 (Open Web Text)

Max Activating Token Index: 765

Text #8

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9753. Min Act: -0.1700

Data Index: 1161961 (Open Web Text)

Max Activating Token Index: 88

Text #9

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9770. Min Act: -0.1700

Data Index: 5871942 (Open Web Text)

Max Activating Token Index: 158

Text #10

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9845. Min Act: -0.1700

Data Index: 5622988 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9783. Min Act: -0.1700

Data Index: 5814820 (Open Web Text)

Max Activating Token Index: 396

Text #12

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9496. Min Act: -0.1700

Data Index: 1170197 (Open Web Text)

Max Activating Token Index: 302

Text #13

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9265. Min Act: -0.1700

Data Index: 3373309 (Open Web Text)

Max Activating Token Index: 790

Text #14

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9494. Min Act: -0.1700

Data Index: 8817455 (Open Web Text)

Max Activating Token Index: 296

Text #15

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9448. Min Act: -0.1700

Data Index: 3362617 (Open Web Text)

Max Activating Token Index: 273

Text #16

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9560. Min Act: -0.1700

Data Index: 5192153 (Open Web Text)

Max Activating Token Index: 718

Text #17

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9519. Min Act: -0.1700

Data Index: 823499 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9442. Min Act: -0.1700

Data Index: 7386647 (Open Web Text)

Max Activating Token Index: 806

Text #19

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9260. Min Act: -0.1700

Data Index: 2218554 (Open Web Text)

Max Activating Token Index: 606