Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 2234 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.1751. Min Act: -0.1700

Data Index: 2223563 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.1438. Min Act: -0.1700

Data Index: 3607800 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.1438. Min Act: -0.1700

Data Index: 3366656 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.1126. Min Act: -0.1700

Data Index: 7684782 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0813. Min Act: -0.1700

Data Index: 5631940 (Open Web Text)

Max Activating Token Index: 750

Text #5

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0813. Min Act: -0.1700

Data Index: 881734 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 3153450 (Open Web Text)

Max Activating Token Index: 1

Text #7

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 5317884 (Open Web Text)

Max Activating Token Index: 1

Text #8

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0188. Min Act: -0.1700

Data Index: 3366655 (Open Web Text)

Max Activating Token Index: 778

Text #9

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 3287791 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 4672252 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 356484 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1699

Data Index: 216559 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 5901851 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1699

Data Index: 499361 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 2664809 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 831543 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 3711335 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 792270 (Open Web Text)

Max Activating Token Index: 289

Text #19

Max Range: 5.1751. Min Range: -5.1751

Max Act: 5.0501. Min Act: -0.1700

Data Index: 699452 (Open Web Text)

Max Activating Token Index: 68