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

Dataset: Open Web Text

Neuron 1968 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: 3.7017. Min Range: -3.7017

Max Act: 3.7017. Min Act: -0.1700

Data Index: 7074711 (Open Web Text)

Max Activating Token Index: 74

Text #1

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.3329. Min Act: -0.1700

Data Index: 8515742 (Open Web Text)

Max Activating Token Index: 110

Text #2

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.2995. Min Act: -0.1700

Data Index: 2446684 (Open Web Text)

Max Activating Token Index: 155

Text #3

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.2855. Min Act: -0.1700

Data Index: 3927547 (Open Web Text)

Max Activating Token Index: 170

Text #4

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.2609. Min Act: -0.1700

Data Index: 5460451 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.2003. Min Act: -0.1700

Data Index: 1795094 (Open Web Text)

Max Activating Token Index: 82

Text #6

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.2030. Min Act: -0.1700

Data Index: 6140070 (Open Web Text)

Max Activating Token Index: 108

Text #7

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.1774. Min Act: -0.1700

Data Index: 200799 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.1967. Min Act: -0.1700

Data Index: 2166630 (Open Web Text)

Max Activating Token Index: 969

Text #9

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.1631. Min Act: -0.1700

Data Index: 2655595 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.1482. Min Act: -0.1700

Data Index: 7131919 (Open Web Text)

Max Activating Token Index: 90

Text #11

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.1431. Min Act: -0.1700

Data Index: 3574969 (Open Web Text)

Max Activating Token Index: 99

Text #12

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.0967. Min Act: -0.1700

Data Index: 437801 (Open Web Text)

Max Activating Token Index: 279

Text #13

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.1135. Min Act: -0.1700

Data Index: 7119530 (Open Web Text)

Max Activating Token Index: 425

Text #14

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.1280. Min Act: -0.1700

Data Index: 3591328 (Open Web Text)

Max Activating Token Index: 31

Text #15

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.0886. Min Act: -0.1700

Data Index: 5075903 (Open Web Text)

Max Activating Token Index: 377

Text #16

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.0721. Min Act: -0.1700

Data Index: 7287315 (Open Web Text)

Max Activating Token Index: 586

Text #17

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.0729. Min Act: -0.1700

Data Index: 5244304 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.0260. Min Act: -0.1700

Data Index: 1484250 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 3.7017. Min Range: -3.7017

Max Act: 3.0378. Min Act: -0.1700

Data Index: 2350554 (Open Web Text)

Max Activating Token Index: 445