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

Dataset: Open Web Text

Neuron 37 in Layer 3

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: 4.5485. Min Range: -4.5485

Max Act: 4.5257. Min Act: -0.1700

Data Index: 4811440 (Open Web Text)

Max Activating Token Index: 1015

Text #1

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.5243. Min Act: -0.1700

Data Index: 5603029 (Open Web Text)

Max Activating Token Index: 412

Text #2

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.5485. Min Act: -0.1700

Data Index: 7731410 (Open Web Text)

Max Activating Token Index: 700

Text #3

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4929. Min Act: -0.1700

Data Index: 5565288 (Open Web Text)

Max Activating Token Index: 102

Text #4

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4797. Min Act: -0.1700

Data Index: 1370248 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4372. Min Act: -0.1700

Data Index: 2379011 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4253. Min Act: -0.1700

Data Index: 7287581 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4253. Min Act: -0.1700

Data Index: 6187922 (Open Web Text)

Max Activating Token Index: 753

Text #8

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4102. Min Act: -0.1700

Data Index: 2275948 (Open Web Text)

Max Activating Token Index: 884

Text #9

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4219. Min Act: -0.1700

Data Index: 8605621 (Open Web Text)

Max Activating Token Index: 372

Text #10

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4501. Min Act: -0.1700

Data Index: 5603034 (Open Web Text)

Max Activating Token Index: 895

Text #11

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.3867. Min Act: -0.1700

Data Index: 7515534 (Open Web Text)

Max Activating Token Index: 836

Text #12

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4123. Min Act: -0.1700

Data Index: 5203528 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4205. Min Act: -0.1700

Data Index: 5432474 (Open Web Text)

Max Activating Token Index: 901

Text #14

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4190. Min Act: -0.1700

Data Index: 6187918 (Open Web Text)

Max Activating Token Index: 571

Text #15

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.3955. Min Act: -0.1700

Data Index: 3766747 (Open Web Text)

Max Activating Token Index: 600

Text #16

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4035. Min Act: -0.1700

Data Index: 3089224 (Open Web Text)

Max Activating Token Index: 936

Text #17

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.4012. Min Act: -0.1700

Data Index: 439683 (Open Web Text)

Max Activating Token Index: 530

Text #18

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.3557. Min Act: -0.1700

Data Index: 5603030 (Open Web Text)

Max Activating Token Index: 124

Text #19

Max Range: 4.5485. Min Range: -4.5485

Max Act: 4.3780. Min Act: -0.1700

Data Index: 4161667 (Open Web Text)

Max Activating Token Index: 893