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

Dataset: Open Web Text

Neuron 674 in Layer 5

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: 7.0689. Min Range: -7.0689

Max Act: 7.0689. Min Act: -0.1700

Data Index: 4246102 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 7.0689. Min Range: -7.0689

Max Act: 7.0489. Min Act: -0.1700

Data Index: 3966651 (Open Web Text)

Max Activating Token Index: 651

Text #2

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.8304. Min Act: -0.1700

Data Index: 3206393 (Open Web Text)

Max Activating Token Index: 592

Text #3

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.9444. Min Act: -0.1700

Data Index: 8358091 (Open Web Text)

Max Activating Token Index: 118

Text #4

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.8892. Min Act: -0.1700

Data Index: 5050279 (Open Web Text)

Max Activating Token Index: 412

Text #5

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.8713. Min Act: -0.1700

Data Index: 6756080 (Open Web Text)

Max Activating Token Index: 680

Text #6

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.7644. Min Act: -0.1700

Data Index: 7201917 (Open Web Text)

Max Activating Token Index: 599

Text #7

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.8315. Min Act: -0.1700

Data Index: 3937547 (Open Web Text)

Max Activating Token Index: 955

Text #8

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.6501. Min Act: -0.1700

Data Index: 7764171 (Open Web Text)

Max Activating Token Index: 508

Text #9

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.8044. Min Act: -0.1700

Data Index: 4316510 (Open Web Text)

Max Activating Token Index: 713

Text #10

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.6788. Min Act: -0.1700

Data Index: 4680252 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.6947. Min Act: -0.1700

Data Index: 7326018 (Open Web Text)

Max Activating Token Index: 416

Text #12

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.5975. Min Act: -0.1700

Data Index: 705432 (Open Web Text)

Max Activating Token Index: 204

Text #13

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.7162. Min Act: -0.1700

Data Index: 7447067 (Open Web Text)

Max Activating Token Index: 417

Text #14

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.6864. Min Act: -0.1700

Data Index: 7648150 (Open Web Text)

Max Activating Token Index: 761

Text #15

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.6796. Min Act: -0.1700

Data Index: 5128195 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.6646. Min Act: -0.1700

Data Index: 2300769 (Open Web Text)

Max Activating Token Index: 998

Text #17

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.5511. Min Act: -0.1700

Data Index: 3489041 (Open Web Text)

Max Activating Token Index: 688

Text #18

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.5625. Min Act: -0.1700

Data Index: 3799098 (Open Web Text)

Max Activating Token Index: 977

Text #19

Max Range: 7.0689. Min Range: -7.0689

Max Act: 6.5781. Min Act: -0.1700

Data Index: 3439388 (Open Web Text)

Max Activating Token Index: 942