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

Dataset: Open Web Text

Neuron 2495 in Layer 0

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: 5.4892. Min Range: -5.4892

Max Act: 5.4892. Min Act: -0.1700

Data Index: 613950 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4551. Min Act: -0.1700

Data Index: 6908795 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4360. Min Act: -0.1700

Data Index: 3599974 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4644. Min Act: -0.1700

Data Index: 390908 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4439. Min Act: -0.1700

Data Index: 7197554 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4327. Min Act: -0.1700

Data Index: 279914 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4142. Min Act: -0.1700

Data Index: 3116137 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4000. Min Act: -0.1700

Data Index: 3362175 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4259. Min Act: -0.1700

Data Index: 7612008 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4243. Min Act: -0.1700

Data Index: 3171355 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4046. Min Act: -0.1700

Data Index: 6920723 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4128. Min Act: -0.1700

Data Index: 3537100 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.3992. Min Act: -0.1700

Data Index: 5859126 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4003. Min Act: -0.1700

Data Index: 5446483 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4256. Min Act: -0.1700

Data Index: 4311952 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4133. Min Act: -0.1700

Data Index: 3735016 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4129. Min Act: -0.1700

Data Index: 1955743 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.4279. Min Act: -0.1700

Data Index: 363568 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.3851. Min Act: -0.1700

Data Index: 1459313 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 5.4892. Min Range: -5.4892

Max Act: 5.3853. Min Act: -0.1700

Data Index: 1470377 (Open Web Text)

Max Activating Token Index: 5