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

Dataset: Open Web Text

Neuron 668 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: 1.6783. Min Range: -1.6783

Max Act: 1.6783. Min Act: -0.1700

Data Index: 5695602 (Open Web Text)

Max Activating Token Index: 128

Text #1

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.6282. Min Act: -0.1700

Data Index: 200511 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.6041. Min Act: -0.1691

Data Index: 4950832 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5947. Min Act: -0.1700

Data Index: 1887747 (Open Web Text)

Max Activating Token Index: 439

Text #4

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5922. Min Act: -0.1700

Data Index: 6050120 (Open Web Text)

Max Activating Token Index: 916

Text #5

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5923. Min Act: -0.1697

Data Index: 5533202 (Open Web Text)

Max Activating Token Index: 546

Text #6

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5903. Min Act: -0.1700

Data Index: 5950160 (Open Web Text)

Max Activating Token Index: 619

Text #7

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5801. Min Act: -0.1699

Data Index: 6712440 (Open Web Text)

Max Activating Token Index: 117

Text #8

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5782. Min Act: -0.1697

Data Index: 6554743 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5645. Min Act: -0.1624

Data Index: 7397611 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5613. Min Act: -0.1700

Data Index: 5087026 (Open Web Text)

Max Activating Token Index: 646

Text #11

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5632. Min Act: -0.1698

Data Index: 2532301 (Open Web Text)

Max Activating Token Index: 156

Text #12

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5574. Min Act: -0.1698

Data Index: 6073586 (Open Web Text)

Max Activating Token Index: 161

Text #13

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5601. Min Act: -0.1700

Data Index: 3415285 (Open Web Text)

Max Activating Token Index: 767

Text #14

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5626. Min Act: -0.1690

Data Index: 3918783 (Open Web Text)

Max Activating Token Index: 522

Text #15

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5471. Min Act: -0.1700

Data Index: 1327816 (Open Web Text)

Max Activating Token Index: 784

Text #16

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5435. Min Act: -0.1697

Data Index: 4786779 (Open Web Text)

Max Activating Token Index: 570

Text #17

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5485. Min Act: -0.1700

Data Index: 507791 (Open Web Text)

Max Activating Token Index: 695

Text #18

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5527. Min Act: -0.1700

Data Index: 4298708 (Open Web Text)

Max Activating Token Index: 964

Text #19

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5468. Min Act: -0.1678

Data Index: 3502362 (Open Web Text)

Max Activating Token Index: 213