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

Dataset: Open Web Text

Neuron 2521 in Layer 3

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: 3.7059. Min Range: -3.7059

Max Act: 3.7059. Min Act: -0.1700

Data Index: 4019740 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.7059. Min Act: -0.1700

Data Index: 6718567 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.6941. Min Act: -0.1700

Data Index: 37950 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.6730. Min Act: -0.1700

Data Index: 8459478 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.6155. Min Act: -0.1700

Data Index: 341285 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.6129. Min Act: -0.1700

Data Index: 501212 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5788. Min Act: -0.1700

Data Index: 4155405 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5741. Min Act: -0.1700

Data Index: 8472363 (Open Web Text)

Max Activating Token Index: 55

Text #8

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5979. Min Act: -0.1700

Data Index: 881453 (Open Web Text)

Max Activating Token Index: 111

Text #9

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5644. Min Act: -0.1700

Data Index: 2021366 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5291. Min Act: -0.1700

Data Index: 7907031 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5353. Min Act: -0.1700

Data Index: 2021365 (Open Web Text)

Max Activating Token Index: 865

Text #12

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5339. Min Act: -0.1700

Data Index: 3168696 (Open Web Text)

Max Activating Token Index: 505

Text #13

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5120. Min Act: -0.1700

Data Index: 4077039 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5405. Min Act: -0.1700

Data Index: 89756 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5135. Min Act: -0.1700

Data Index: 4109648 (Open Web Text)

Max Activating Token Index: 67

Text #16

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5268. Min Act: -0.1700

Data Index: 5446920 (Open Web Text)

Max Activating Token Index: 205

Text #17

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5107. Min Act: -0.1700

Data Index: 643046 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5025. Min Act: -0.1700

Data Index: 6245912 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 3.7059. Min Range: -3.7059

Max Act: 3.5060. Min Act: -0.1700

Data Index: 630404 (Open Web Text)

Max Activating Token Index: 105