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

Dataset: Open Web Text

Neuron 1835 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: 5.3954. Min Range: -5.3954

Max Act: 5.3954. Min Act: -0.1700

Data Index: 8798330 (Open Web Text)

Max Activating Token Index: 1003

Text #1

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.1815. Min Act: -0.1700

Data Index: 1332726 (Open Web Text)

Max Activating Token Index: 392

Text #2

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.1784. Min Act: -0.1700

Data Index: 629054 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.1452. Min Act: -0.1700

Data Index: 5726209 (Open Web Text)

Max Activating Token Index: 912

Text #4

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.1804. Min Act: -0.1700

Data Index: 4558672 (Open Web Text)

Max Activating Token Index: 409

Text #5

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.1488. Min Act: -0.1700

Data Index: 7437778 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.1160. Min Act: -0.1700

Data Index: 629055 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.1231. Min Act: -0.1700

Data Index: 655406 (Open Web Text)

Max Activating Token Index: 204

Text #8

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.1558. Min Act: -0.1700

Data Index: 4349689 (Open Web Text)

Max Activating Token Index: 662

Text #9

Max Range: 5.3954. Min Range: -5.3954

Max Act: 4.9552. Min Act: -0.1700

Data Index: 3607551 (Open Web Text)

Max Activating Token Index: 704

Text #10

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.0596. Min Act: -0.1700

Data Index: 156538 (Open Web Text)

Max Activating Token Index: 854

Text #11

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.0318. Min Act: -0.1700

Data Index: 6359307 (Open Web Text)

Max Activating Token Index: 647

Text #12

Max Range: 5.3954. Min Range: -5.3954

Max Act: 4.9781. Min Act: -0.1700

Data Index: 7813255 (Open Web Text)

Max Activating Token Index: 241

Text #13

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.0106. Min Act: -0.1700

Data Index: 3522286 (Open Web Text)

Max Activating Token Index: 804

Text #14

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.0392. Min Act: -0.1700

Data Index: 727611 (Open Web Text)

Max Activating Token Index: 487

Text #15

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.0109. Min Act: -0.1700

Data Index: 6186112 (Open Web Text)

Max Activating Token Index: 149

Text #16

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.0185. Min Act: -0.1700

Data Index: 7436818 (Open Web Text)

Max Activating Token Index: 155

Text #17

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.0309. Min Act: -0.1700

Data Index: 7332006 (Open Web Text)

Max Activating Token Index: 949

Text #18

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.0709. Min Act: -0.1700

Data Index: 3004315 (Open Web Text)

Max Activating Token Index: 819

Text #19

Max Range: 5.3954. Min Range: -5.3954

Max Act: 5.0230. Min Act: -0.1700

Data Index: 3687145 (Open Web Text)

Max Activating Token Index: 705