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

Dataset: Open Web Text

Neuron 2754 in Layer 4

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: 4.8008. Min Range: -4.8008

Max Act: 4.8008. Min Act: -0.1700

Data Index: 2071244 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.7469. Min Act: -0.1700

Data Index: 5321585 (Open Web Text)

Max Activating Token Index: 217

Text #2

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.6641. Min Act: -0.1700

Data Index: 4525973 (Open Web Text)

Max Activating Token Index: 199

Text #3

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5957. Min Act: -0.1700

Data Index: 1897809 (Open Web Text)

Max Activating Token Index: 353

Text #4

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5776. Min Act: -0.1700

Data Index: 2986746 (Open Web Text)

Max Activating Token Index: 547

Text #5

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5956. Min Act: -0.1700

Data Index: 3000544 (Open Web Text)

Max Activating Token Index: 501

Text #6

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5419. Min Act: -0.1700

Data Index: 3795999 (Open Web Text)

Max Activating Token Index: 92

Text #7

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5519. Min Act: -0.1700

Data Index: 4016234 (Open Web Text)

Max Activating Token Index: 251

Text #8

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5275. Min Act: -0.1700

Data Index: 7116181 (Open Web Text)

Max Activating Token Index: 221

Text #9

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5229. Min Act: -0.1700

Data Index: 8159774 (Open Web Text)

Max Activating Token Index: 185

Text #10

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5002. Min Act: -0.1700

Data Index: 1016521 (Open Web Text)

Max Activating Token Index: 550

Text #11

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.4943. Min Act: -0.1700

Data Index: 5126665 (Open Web Text)

Max Activating Token Index: 575

Text #12

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.4848. Min Act: -0.1700

Data Index: 2764343 (Open Web Text)

Max Activating Token Index: 586

Text #13

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5217. Min Act: -0.1700

Data Index: 8495333 (Open Web Text)

Max Activating Token Index: 406

Text #14

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5017. Min Act: -0.1700

Data Index: 2078732 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.5045. Min Act: -0.1700

Data Index: 4704449 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.4706. Min Act: -0.1700

Data Index: 3139530 (Open Web Text)

Max Activating Token Index: 315

Text #17

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.4723. Min Act: -0.1700

Data Index: 3749113 (Open Web Text)

Max Activating Token Index: 110

Text #18

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.4437. Min Act: -0.1700

Data Index: 5863914 (Open Web Text)

Max Activating Token Index: 793

Text #19

Max Range: 4.8008. Min Range: -4.8008

Max Act: 4.4519. Min Act: -0.1700

Data Index: 6158433 (Open Web Text)

Max Activating Token Index: 705