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

Dataset: Open Web Text

Neuron 261 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: 4.2599. Min Range: -4.2599

Max Act: 4.2599. Min Act: -0.1700

Data Index: 4793626 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.2599. Min Range: -4.2599

Max Act: 4.1503. Min Act: -0.1700

Data Index: 5227260 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.2599. Min Range: -4.2599

Max Act: 4.1503. Min Act: -0.1700

Data Index: 707756 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.2599. Min Range: -4.2599

Max Act: 4.1644. Min Act: -0.1700

Data Index: 8722801 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.2599. Min Range: -4.2599

Max Act: 4.1644. Min Act: -0.1700

Data Index: 7688098 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.2599. Min Range: -4.2599

Max Act: 4.0917. Min Act: -0.1700

Data Index: 4832172 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.9971. Min Act: -0.1700

Data Index: 2920734 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.2599. Min Range: -4.2599

Max Act: 4.0049. Min Act: -0.1700

Data Index: 1245203 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.9984. Min Act: -0.1700

Data Index: 98875 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.9401. Min Act: -0.1700

Data Index: 7362797 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.9192. Min Act: -0.1700

Data Index: 4484117 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.9123. Min Act: -0.1700

Data Index: 7146509 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.8935. Min Act: -0.1700

Data Index: 4659292 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.8896. Min Act: -0.1700

Data Index: 6249162 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.8863. Min Act: -0.1700

Data Index: 7348921 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.8803. Min Act: -0.1700

Data Index: 2712733 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.8806. Min Act: -0.1700

Data Index: 3916667 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.8624. Min Act: -0.1700

Data Index: 8804262 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.8849. Min Act: -0.1700

Data Index: 5808210 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.2599. Min Range: -4.2599

Max Act: 3.8316. Min Act: -0.1700

Data Index: 1120274 (Open Web Text)

Max Activating Token Index: 6