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

Dataset: Open Web Text

Neuron 125 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: 3.8336. Min Range: -3.8336

Max Act: 3.8336. Min Act: -0.1691

Data Index: 4349447 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7744. Min Act: -0.1700

Data Index: 2746206 (Open Web Text)

Max Activating Token Index: 39

Text #2

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7439. Min Act: -0.1700

Data Index: 4702744 (Open Web Text)

Max Activating Token Index: 167

Text #3

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7416. Min Act: -0.1700

Data Index: 4702740 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7281. Min Act: -0.1700

Data Index: 5153748 (Open Web Text)

Max Activating Token Index: 832

Text #5

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6911. Min Act: -0.1700

Data Index: 5056225 (Open Web Text)

Max Activating Token Index: 28

Text #6

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7052. Min Act: -0.1700

Data Index: 8567566 (Open Web Text)

Max Activating Token Index: 121

Text #7

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6855. Min Act: -0.1700

Data Index: 4951645 (Open Web Text)

Max Activating Token Index: 481

Text #8

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7093. Min Act: -0.1693

Data Index: 8504033 (Open Web Text)

Max Activating Token Index: 155

Text #9

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6799. Min Act: -0.1700

Data Index: 1676707 (Open Web Text)

Max Activating Token Index: 820

Text #10

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6917. Min Act: -0.1700

Data Index: 7970618 (Open Web Text)

Max Activating Token Index: 745

Text #11

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6958. Min Act: -0.1700

Data Index: 6612115 (Open Web Text)

Max Activating Token Index: 905

Text #12

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6681. Min Act: -0.1698

Data Index: 2462216 (Open Web Text)

Max Activating Token Index: 570

Text #13

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6847. Min Act: -0.1695

Data Index: 3560447 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6931. Min Act: -0.1696

Data Index: 5434038 (Open Web Text)

Max Activating Token Index: 484

Text #15

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7031. Min Act: -0.1700

Data Index: 5153754 (Open Web Text)

Max Activating Token Index: 164

Text #16

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6998. Min Act: -0.1696

Data Index: 1676829 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6683. Min Act: -0.1674

Data Index: 1867580 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6541. Min Act: -0.1697

Data Index: 2246027 (Open Web Text)

Max Activating Token Index: 354

Text #19

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6972. Min Act: -0.1700

Data Index: 4951649 (Open Web Text)

Max Activating Token Index: 706