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

Dataset: Open Web Text

Neuron 2427 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: 3.4544. Min Range: -3.4544

Max Act: 3.4544. Min Act: -0.1700

Data Index: 6247428 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.4436. Min Act: -0.1700

Data Index: 5240237 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.4360. Min Act: -0.1700

Data Index: 3373342 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.4195. Min Act: -0.1700

Data Index: 5446763 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.3834. Min Act: -0.1700

Data Index: 46938 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.3717. Min Act: -0.1700

Data Index: 6890282 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.3470. Min Act: -0.1700

Data Index: 307742 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.3140. Min Act: -0.1700

Data Index: 7398151 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2956. Min Act: -0.1700

Data Index: 6676348 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2853. Min Act: -0.1700

Data Index: 3721718 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2603. Min Act: -0.1700

Data Index: 2937279 (Open Web Text)

Max Activating Token Index: 933

Text #11

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2898. Min Act: -0.1700

Data Index: 1903668 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2751. Min Act: -0.1700

Data Index: 3359734 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2616. Min Act: -0.1700

Data Index: 806523 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2696. Min Act: -0.1700

Data Index: 3895535 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2471. Min Act: -0.1700

Data Index: 4368427 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2446. Min Act: -0.1700

Data Index: 3761101 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2562. Min Act: -0.1700

Data Index: 1433791 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2565. Min Act: -0.1700

Data Index: 4857579 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.4544. Min Range: -3.4544

Max Act: 3.2404. Min Act: -0.1700

Data Index: 3702323 (Open Web Text)

Max Activating Token Index: 2