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

Dataset: Open Web Text

Neuron 2005 in Layer 5

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: 4.7527. Min Range: -4.7527

Max Act: 4.7527. Min Act: -0.1700

Data Index: 1204223 (Open Web Text)

Max Activating Token Index: 880

Text #1

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.7250. Min Act: -0.1700

Data Index: 2284201 (Open Web Text)

Max Activating Token Index: 825

Text #2

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.6552. Min Act: -0.1700

Data Index: 6054058 (Open Web Text)

Max Activating Token Index: 133

Text #3

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.6413. Min Act: -0.1700

Data Index: 1295904 (Open Web Text)

Max Activating Token Index: 597

Text #4

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5644. Min Act: -0.1700

Data Index: 898644 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5912. Min Act: -0.1700

Data Index: 4174111 (Open Web Text)

Max Activating Token Index: 664

Text #6

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.6096. Min Act: -0.1700

Data Index: 5954796 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.6145. Min Act: -0.1700

Data Index: 8675701 (Open Web Text)

Max Activating Token Index: 91

Text #8

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5724. Min Act: -0.1700

Data Index: 2185054 (Open Web Text)

Max Activating Token Index: 644

Text #9

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5889. Min Act: -0.1700

Data Index: 4355895 (Open Web Text)

Max Activating Token Index: 751

Text #10

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5778. Min Act: -0.1700

Data Index: 6856919 (Open Web Text)

Max Activating Token Index: 783

Text #11

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5547. Min Act: -0.1700

Data Index: 430368 (Open Web Text)

Max Activating Token Index: 425

Text #12

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5212. Min Act: -0.1700

Data Index: 45514 (Open Web Text)

Max Activating Token Index: 444

Text #13

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5298. Min Act: -0.1700

Data Index: 7032885 (Open Web Text)

Max Activating Token Index: 951

Text #14

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5173. Min Act: -0.1700

Data Index: 2434885 (Open Web Text)

Max Activating Token Index: 632

Text #15

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.4942. Min Act: -0.1700

Data Index: 2033791 (Open Web Text)

Max Activating Token Index: 673

Text #16

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5036. Min Act: -0.1700

Data Index: 5868185 (Open Web Text)

Max Activating Token Index: 389

Text #17

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.5126. Min Act: -0.1700

Data Index: 8339796 (Open Web Text)

Max Activating Token Index: 968

Text #18

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.4546. Min Act: -0.1700

Data Index: 3252179 (Open Web Text)

Max Activating Token Index: 330

Text #19

Max Range: 4.7527. Min Range: -4.7527

Max Act: 4.4390. Min Act: -0.1700

Data Index: 865599 (Open Web Text)

Max Activating Token Index: 313