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

Dataset: Open Web Text

Neuron 2203 in Layer 2

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: 3.3617. Min Range: -3.3617

Max Act: 3.3617. Min Act: -0.1700

Data Index: 4226608 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.1083. Min Act: -0.1700

Data Index: 7072952 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.0756. Min Act: -0.1700

Data Index: 7506025 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.0648. Min Act: -0.1700

Data Index: 3270439 (Open Web Text)

Max Activating Token Index: 727

Text #4

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.0449. Min Act: -0.1700

Data Index: 8190647 (Open Web Text)

Max Activating Token Index: 246

Text #5

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.0601. Min Act: -0.1700

Data Index: 3270440 (Open Web Text)

Max Activating Token Index: 164

Text #6

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.0515. Min Act: -0.1700

Data Index: 2217676 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.0427. Min Act: -0.1700

Data Index: 3349135 (Open Web Text)

Max Activating Token Index: 142

Text #8

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.9647. Min Act: -0.1700

Data Index: 4864327 (Open Web Text)

Max Activating Token Index: 695

Text #9

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.0068. Min Act: -0.1700

Data Index: 8190646 (Open Web Text)

Max Activating Token Index: 1006

Text #10

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.0030. Min Act: -0.1700

Data Index: 1149500 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.9988. Min Act: -0.1700

Data Index: 3069781 (Open Web Text)

Max Activating Token Index: 877

Text #12

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.0007. Min Act: -0.1700

Data Index: 5147889 (Open Web Text)

Max Activating Token Index: 256

Text #13

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.9679. Min Act: -0.1700

Data Index: 7398753 (Open Web Text)

Max Activating Token Index: 770

Text #14

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.9725. Min Act: -0.1700

Data Index: 860818 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.9531. Min Act: -0.1700

Data Index: 970954 (Open Web Text)

Max Activating Token Index: 93

Text #16

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.9556. Min Act: -0.1700

Data Index: 553485 (Open Web Text)

Max Activating Token Index: 131

Text #17

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.9308. Min Act: -0.1700

Data Index: 1428906 (Open Web Text)

Max Activating Token Index: 710

Text #18

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.9188. Min Act: -0.1700

Data Index: 7851484 (Open Web Text)

Max Activating Token Index: 685

Text #19

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.9153. Min Act: -0.1700

Data Index: 6950937 (Open Web Text)

Max Activating Token Index: 918