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

Dataset: Open Web Text

Neuron 506 in Layer 1

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: 1.4128. Min Range: -1.4128

Max Act: 1.4089. Min Act: -0.1700

Data Index: 3937080 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.4128. Min Act: -0.1698

Data Index: 4131914 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.4089. Min Act: -0.1699

Data Index: 8481575 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.4089. Min Act: -0.1699

Data Index: 5009385 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.4089. Min Act: -0.1698

Data Index: 6280675 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.4095. Min Act: -0.1700

Data Index: 5364801 (Open Web Text)

Max Activating Token Index: 93

Text #6

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3754. Min Act: -0.1469

Data Index: 4776619 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3804. Min Act: -0.1700

Data Index: 8100296 (Open Web Text)

Max Activating Token Index: 96

Text #8

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3861. Min Act: -0.1700

Data Index: 3036331 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3812. Min Act: -0.1696

Data Index: 7659446 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3615. Min Act: -0.1695

Data Index: 2476641 (Open Web Text)

Max Activating Token Index: 260

Text #11

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3578. Min Act: -0.1700

Data Index: 6598137 (Open Web Text)

Max Activating Token Index: 465

Text #12

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3435. Min Act: -0.1700

Data Index: 1851159 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3359. Min Act: -0.1700

Data Index: 7287520 (Open Web Text)

Max Activating Token Index: 712

Text #14

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3476. Min Act: -0.1700

Data Index: 5001872 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3519. Min Act: -0.1700

Data Index: 569732 (Open Web Text)

Max Activating Token Index: 468

Text #16

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3483. Min Act: -0.1696

Data Index: 1810621 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3455. Min Act: -0.1700

Data Index: 6598140 (Open Web Text)

Max Activating Token Index: 758

Text #18

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3352. Min Act: -0.1679

Data Index: 698720 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3367. Min Act: -0.1700

Data Index: 6744653 (Open Web Text)

Max Activating Token Index: 456