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

Dataset: Open Web Text

Neuron 1965 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: 4.1083. Min Range: -4.1083

Max Act: 4.1083. Min Act: -0.1700

Data Index: 2577128 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.1083. Min Range: -4.1083

Max Act: 4.0661. Min Act: -0.1700

Data Index: 1983761 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.1083. Min Range: -4.1083

Max Act: 4.0305. Min Act: -0.1700

Data Index: 1615718 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.1083. Min Range: -4.1083

Max Act: 4.0295. Min Act: -0.1700

Data Index: 1862924 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.1083. Min Range: -4.1083

Max Act: 4.0392. Min Act: -0.1700

Data Index: 5994974 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.1083. Min Range: -4.1083

Max Act: 4.0067. Min Act: -0.1700

Data Index: 5755048 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.1083. Min Range: -4.1083

Max Act: 4.0127. Min Act: -0.1700

Data Index: 494905 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.1083. Min Range: -4.1083

Max Act: 3.9965. Min Act: -0.1700

Data Index: 4181503 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.1083. Min Range: -4.1083

Max Act: 4.0214. Min Act: -0.1700

Data Index: 6091011 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.1083. Min Range: -4.1083

Max Act: 4.0113. Min Act: -0.1700

Data Index: 2187399 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.1083. Min Range: -4.1083

Max Act: 4.0113. Min Act: -0.1700

Data Index: 1682097 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.1083. Min Range: -4.1083

Max Act: 3.9955. Min Act: -0.1700

Data Index: 6700122 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.1083. Min Range: -4.1083

Max Act: 3.9920. Min Act: -0.1700

Data Index: 2160782 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.1083. Min Range: -4.1083

Max Act: 3.9657. Min Act: -0.1700

Data Index: 5807674 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.1083. Min Range: -4.1083

Max Act: 3.9415. Min Act: -0.1700

Data Index: 1983184 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 4.1083. Min Range: -4.1083

Max Act: 3.9538. Min Act: -0.1700

Data Index: 3078244 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.1083. Min Range: -4.1083

Max Act: 3.9350. Min Act: -0.1700

Data Index: 4493819 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.1083. Min Range: -4.1083

Max Act: 3.9428. Min Act: -0.1700

Data Index: 5282536 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.1083. Min Range: -4.1083

Max Act: 3.9458. Min Act: -0.1700

Data Index: 5373384 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.1083. Min Range: -4.1083

Max Act: 3.9272. Min Act: -0.1700

Data Index: 5912892 (Open Web Text)

Max Activating Token Index: 8