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

Dataset: Open Web Text

Neuron 2567 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: 3.4037. Min Range: -3.4037

Max Act: 3.4037. Min Act: -0.1700

Data Index: 1879026 (Open Web Text)

Max Activating Token Index: 85

Text #1

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2871. Min Act: -0.1700

Data Index: 7458497 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2541. Min Act: -0.1700

Data Index: 2468168 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2633. Min Act: -0.1700

Data Index: 4324064 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2571. Min Act: -0.1700

Data Index: 4171333 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2430. Min Act: -0.1700

Data Index: 2183802 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2320. Min Act: -0.1700

Data Index: 191870 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2384. Min Act: -0.1700

Data Index: 1722399 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2273. Min Act: -0.1700

Data Index: 4482139 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2200. Min Act: -0.1700

Data Index: 2404134 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2219. Min Act: -0.1700

Data Index: 1841572 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2126. Min Act: -0.1700

Data Index: 3961529 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2204. Min Act: -0.1700

Data Index: 4526636 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2143. Min Act: -0.1700

Data Index: 3846687 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2147. Min Act: -0.1700

Data Index: 5525113 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2091. Min Act: -0.1700

Data Index: 6034260 (Open Web Text)

Max Activating Token Index: 28

Text #16

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2133. Min Act: -0.1700

Data Index: 6496010 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2002. Min Act: -0.1700

Data Index: 6778087 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2010. Min Act: -0.1700

Data Index: 1752349 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2145. Min Act: -0.1700

Data Index: 6905927 (Open Web Text)

Max Activating Token Index: 35