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

Dataset: Open Web Text

Neuron 1875 in Layer 4

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: 4.0317. Min Range: -4.0317

Max Act: 4.0317. Min Act: -0.1700

Data Index: 1212573 (Open Web Text)

Max Activating Token Index: 673

Text #1

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9982. Min Act: -0.1700

Data Index: 8427551 (Open Web Text)

Max Activating Token Index: 811

Text #2

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9592. Min Act: -0.1700

Data Index: 2768109 (Open Web Text)

Max Activating Token Index: 911

Text #3

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9580. Min Act: -0.1700

Data Index: 1062781 (Open Web Text)

Max Activating Token Index: 425

Text #4

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9718. Min Act: -0.1700

Data Index: 2085930 (Open Web Text)

Max Activating Token Index: 359

Text #5

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9660. Min Act: -0.1700

Data Index: 6544967 (Open Web Text)

Max Activating Token Index: 833

Text #6

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9651. Min Act: -0.1700

Data Index: 1474359 (Open Web Text)

Max Activating Token Index: 301

Text #7

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9670. Min Act: -0.1700

Data Index: 7996623 (Open Web Text)

Max Activating Token Index: 719

Text #8

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9455. Min Act: -0.1700

Data Index: 4865377 (Open Web Text)

Max Activating Token Index: 620

Text #9

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9223. Min Act: -0.1700

Data Index: 653600 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9060. Min Act: -0.1700

Data Index: 4863166 (Open Web Text)

Max Activating Token Index: 378

Text #11

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9289. Min Act: -0.1700

Data Index: 5177651 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9285. Min Act: -0.1700

Data Index: 5755126 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9289. Min Act: -0.1700

Data Index: 984732 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9411. Min Act: -0.1700

Data Index: 4493097 (Open Web Text)

Max Activating Token Index: 636

Text #15

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9289. Min Act: -0.1700

Data Index: 4257627 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9538. Min Act: -0.1700

Data Index: 4189110 (Open Web Text)

Max Activating Token Index: 551

Text #17

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9497. Min Act: -0.1700

Data Index: 7163578 (Open Web Text)

Max Activating Token Index: 941

Text #18

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9441. Min Act: -0.1700

Data Index: 3245120 (Open Web Text)

Max Activating Token Index: 503

Text #19

Max Range: 4.0317. Min Range: -4.0317

Max Act: 3.9109. Min Act: -0.1700

Data Index: 3696607 (Open Web Text)

Max Activating Token Index: 778