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

Dataset: Open Web Text

Neuron 62 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: 3.0819. Min Range: -3.0819

Max Act: 3.0819. Min Act: -0.1700

Data Index: 7100301 (Open Web Text)

Max Activating Token Index: 167

Text #1

Max Range: 3.0819. Min Range: -3.0819

Max Act: 3.0669. Min Act: -0.1700

Data Index: 8014783 (Open Web Text)

Max Activating Token Index: 826

Text #2

Max Range: 3.0819. Min Range: -3.0819

Max Act: 3.0354. Min Act: -0.1700

Data Index: 7014258 (Open Web Text)

Max Activating Token Index: 120

Text #3

Max Range: 3.0819. Min Range: -3.0819

Max Act: 3.0172. Min Act: -0.1700

Data Index: 3434901 (Open Web Text)

Max Activating Token Index: 703

Text #4

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.9320. Min Act: -0.1700

Data Index: 8555939 (Open Web Text)

Max Activating Token Index: 504

Text #5

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.9327. Min Act: -0.1700

Data Index: 961343 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.9097. Min Act: -0.1700

Data Index: 3547355 (Open Web Text)

Max Activating Token Index: 261

Text #7

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.9154. Min Act: -0.1700

Data Index: 8144007 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.9198. Min Act: -0.1700

Data Index: 1799412 (Open Web Text)

Max Activating Token Index: 91

Text #9

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.8762. Min Act: -0.1700

Data Index: 2196767 (Open Web Text)

Max Activating Token Index: 294

Text #10

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.8817. Min Act: -0.1700

Data Index: 6617550 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.8843. Min Act: -0.1700

Data Index: 8756316 (Open Web Text)

Max Activating Token Index: 452

Text #12

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.8881. Min Act: -0.1700

Data Index: 3180206 (Open Web Text)

Max Activating Token Index: 667

Text #13

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.9002. Min Act: -0.1700

Data Index: 2711706 (Open Web Text)

Max Activating Token Index: 970

Text #14

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.8318. Min Act: -0.1700

Data Index: 6211257 (Open Web Text)

Max Activating Token Index: 626

Text #15

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.8761. Min Act: -0.1700

Data Index: 5705037 (Open Web Text)

Max Activating Token Index: 195

Text #16

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.9090. Min Act: -0.1700

Data Index: 729017 (Open Web Text)

Max Activating Token Index: 782

Text #17

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.8888. Min Act: -0.1700

Data Index: 58513 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.8442. Min Act: -0.1700

Data Index: 6359356 (Open Web Text)

Max Activating Token Index: 122

Text #19

Max Range: 3.0819. Min Range: -3.0819

Max Act: 2.8954. Min Act: -0.1700

Data Index: 2854491 (Open Web Text)

Max Activating Token Index: 870