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

Dataset: Open Web Text

Neuron 822 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: 3.3328. Min Range: -3.3328

Max Act: 3.3110. Min Act: -0.1700

Data Index: 3675019 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.3328. Min Act: -0.1700

Data Index: 4345324 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.3110. Min Act: -0.1700

Data Index: 8613537 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.2839. Min Act: -0.1700

Data Index: 4911369 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.2573. Min Act: -0.1700

Data Index: 883222 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.2573. Min Act: -0.1700

Data Index: 5021640 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.2573. Min Act: -0.1700

Data Index: 3464522 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.2573. Min Act: -0.1700

Data Index: 5609611 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.2573. Min Act: -0.1700

Data Index: 4839009 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.2133. Min Act: -0.1700

Data Index: 7809416 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1908. Min Act: -0.1700

Data Index: 3549263 (Open Web Text)

Max Activating Token Index: 287

Text #11

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1528. Min Act: -0.1700

Data Index: 7963344 (Open Web Text)

Max Activating Token Index: 872

Text #12

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1831. Min Act: -0.1700

Data Index: 1323883 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1662. Min Act: -0.1700

Data Index: 2576245 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1848. Min Act: -0.1700

Data Index: 570651 (Open Web Text)

Max Activating Token Index: 980

Text #15

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1772. Min Act: -0.1700

Data Index: 984432 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1602. Min Act: -0.1700

Data Index: 2376013 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1650. Min Act: -0.1700

Data Index: 5401722 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1559. Min Act: -0.1700

Data Index: 2005149 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1637. Min Act: -0.1700

Data Index: 7281447 (Open Web Text)

Max Activating Token Index: 846