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

Dataset: Open Web Text

Neuron 1820 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: 4.2363. Min Range: -4.2363

Max Act: 4.2363. Min Act: -0.1700

Data Index: 7445565 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.2363. Min Range: -4.2363

Max Act: 4.0880. Min Act: -0.1700

Data Index: 2959323 (Open Web Text)

Max Activating Token Index: 56

Text #2

Max Range: 4.2363. Min Range: -4.2363

Max Act: 4.0876. Min Act: -0.1700

Data Index: 412439 (Open Web Text)

Max Activating Token Index: 360

Text #3

Max Range: 4.2363. Min Range: -4.2363

Max Act: 4.0876. Min Act: -0.1700

Data Index: 1609307 (Open Web Text)

Max Activating Token Index: 993

Text #4

Max Range: 4.2363. Min Range: -4.2363

Max Act: 4.0369. Min Act: -0.1700

Data Index: 5612358 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 4.2363. Min Range: -4.2363

Max Act: 4.0193. Min Act: -0.1700

Data Index: 1615731 (Open Web Text)

Max Activating Token Index: 222

Text #6

Max Range: 4.2363. Min Range: -4.2363

Max Act: 4.0189. Min Act: -0.1700

Data Index: 3352606 (Open Web Text)

Max Activating Token Index: 55

Text #7

Max Range: 4.2363. Min Range: -4.2363

Max Act: 4.0002. Min Act: -0.1700

Data Index: 3617538 (Open Web Text)

Max Activating Token Index: 153

Text #8

Max Range: 4.2363. Min Range: -4.2363

Max Act: 4.0043. Min Act: -0.1700

Data Index: 7801610 (Open Web Text)

Max Activating Token Index: 707

Text #9

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9791. Min Act: -0.1700

Data Index: 2921775 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9804. Min Act: -0.1700

Data Index: 1538913 (Open Web Text)

Max Activating Token Index: 323

Text #11

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9747. Min Act: -0.1700

Data Index: 5049086 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9718. Min Act: -0.1700

Data Index: 2720807 (Open Web Text)

Max Activating Token Index: 766

Text #13

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9436. Min Act: -0.1700

Data Index: 6534090 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9383. Min Act: -0.1700

Data Index: 1226150 (Open Web Text)

Max Activating Token Index: 505

Text #15

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9421. Min Act: -0.1700

Data Index: 6179661 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9521. Min Act: -0.1700

Data Index: 5112013 (Open Web Text)

Max Activating Token Index: 545

Text #17

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9423. Min Act: -0.1700

Data Index: 4902289 (Open Web Text)

Max Activating Token Index: 859

Text #18

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9736. Min Act: -0.1700

Data Index: 4226754 (Open Web Text)

Max Activating Token Index: 396

Text #19

Max Range: 4.2363. Min Range: -4.2363

Max Act: 3.9495. Min Act: -0.1700

Data Index: 2192816 (Open Web Text)

Max Activating Token Index: 782