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

Dataset: Open Web Text

Neuron 2675 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: 3.2760. Min Range: -3.2760

Max Act: 3.2760. Min Act: -0.1700

Data Index: 1319971 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.2594. Min Act: -0.1700

Data Index: 7799398 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.1764. Min Act: -0.1700

Data Index: 7391617 (Open Web Text)

Max Activating Token Index: 39

Text #3

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.1518. Min Act: -0.1700

Data Index: 3126513 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.1184. Min Act: -0.1700

Data Index: 6507528 (Open Web Text)

Max Activating Token Index: 979

Text #5

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.1374. Min Act: -0.1700

Data Index: 3167633 (Open Web Text)

Max Activating Token Index: 839

Text #6

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.1106. Min Act: -0.1700

Data Index: 7011679 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0907. Min Act: -0.1700

Data Index: 2845325 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0925. Min Act: -0.1700

Data Index: 6891604 (Open Web Text)

Max Activating Token Index: 255

Text #9

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0957. Min Act: -0.1700

Data Index: 363047 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0757. Min Act: -0.1700

Data Index: 8546638 (Open Web Text)

Max Activating Token Index: 24

Text #11

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0746. Min Act: -0.1700

Data Index: 1793604 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0634. Min Act: -0.1700

Data Index: 4823837 (Open Web Text)

Max Activating Token Index: 390

Text #13

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0755. Min Act: -0.1700

Data Index: 1859885 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0615. Min Act: -0.1700

Data Index: 8451797 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0662. Min Act: -0.1700

Data Index: 2607560 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0526. Min Act: -0.1700

Data Index: 2333895 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0329. Min Act: -0.1700

Data Index: 1166824 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0481. Min Act: -0.1700

Data Index: 5964864 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 3.2760. Min Range: -3.2760

Max Act: 3.0497. Min Act: -0.1700

Data Index: 2189640 (Open Web Text)

Max Activating Token Index: 39