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

Dataset: Open Web Text

Neuron 2290 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: 6.2694. Min Range: -6.2694

Max Act: 6.2694. Min Act: -0.1700

Data Index: 8696033 (Open Web Text)

Max Activating Token Index: 498

Text #1

Max Range: 6.2694. Min Range: -6.2694

Max Act: 6.1449. Min Act: -0.1700

Data Index: 6848718 (Open Web Text)

Max Activating Token Index: 511

Text #2

Max Range: 6.2694. Min Range: -6.2694

Max Act: 6.0472. Min Act: -0.1699

Data Index: 4774348 (Open Web Text)

Max Activating Token Index: 235

Text #3

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.9931. Min Act: -0.1689

Data Index: 5865998 (Open Web Text)

Max Activating Token Index: 516

Text #4

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.9712. Min Act: -0.1698

Data Index: 6387095 (Open Web Text)

Max Activating Token Index: 100

Text #5

Max Range: 6.2694. Min Range: -6.2694

Max Act: 6.0415. Min Act: -0.1700

Data Index: 2328998 (Open Web Text)

Max Activating Token Index: 400

Text #6

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.9103. Min Act: -0.1700

Data Index: 3806898 (Open Web Text)

Max Activating Token Index: 238

Text #7

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.9678. Min Act: -0.1700

Data Index: 911071 (Open Web Text)

Max Activating Token Index: 355

Text #8

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.8210. Min Act: -0.1700

Data Index: 7291884 (Open Web Text)

Max Activating Token Index: 580

Text #9

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.8348. Min Act: -0.1700

Data Index: 2538119 (Open Web Text)

Max Activating Token Index: 991

Text #10

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.9139. Min Act: -0.1700

Data Index: 5792059 (Open Web Text)

Max Activating Token Index: 530

Text #11

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.8622. Min Act: -0.1700

Data Index: 5182799 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.8987. Min Act: -0.1700

Data Index: 6779725 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.9311. Min Act: -0.1699

Data Index: 2779204 (Open Web Text)

Max Activating Token Index: 665

Text #14

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.7774. Min Act: -0.1693

Data Index: 8793573 (Open Web Text)

Max Activating Token Index: 568

Text #15

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.8027. Min Act: -0.1700

Data Index: 7305826 (Open Web Text)

Max Activating Token Index: 546

Text #16

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.8464. Min Act: -0.1698

Data Index: 2408417 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.7464. Min Act: -0.1699

Data Index: 3726926 (Open Web Text)

Max Activating Token Index: 649

Text #18

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.8139. Min Act: -0.1700

Data Index: 3834078 (Open Web Text)

Max Activating Token Index: 93

Text #19

Max Range: 6.2694. Min Range: -6.2694

Max Act: 5.8615. Min Act: -0.1700

Data Index: 5865997 (Open Web Text)

Max Activating Token Index: 955