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

Dataset: Open Web Text

Neuron 1887 in Layer 6

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: 3.5685. Min Range: -3.5685

Max Act: 3.5685. Min Act: -0.1700

Data Index: 4836687 (Open Web Text)

Max Activating Token Index: 284

Text #1

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.5077. Min Act: -0.1700

Data Index: 4060992 (Open Web Text)

Max Activating Token Index: 478

Text #2

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4732. Min Act: -0.1700

Data Index: 4909395 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4989. Min Act: -0.1700

Data Index: 2668896 (Open Web Text)

Max Activating Token Index: 190

Text #4

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4567. Min Act: -0.1700

Data Index: 4909394 (Open Web Text)

Max Activating Token Index: 529

Text #5

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4588. Min Act: -0.1700

Data Index: 5243504 (Open Web Text)

Max Activating Token Index: 1011

Text #6

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4492. Min Act: -0.1700

Data Index: 5179790 (Open Web Text)

Max Activating Token Index: 589

Text #7

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4773. Min Act: -0.1700

Data Index: 8804662 (Open Web Text)

Max Activating Token Index: 994

Text #8

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4544. Min Act: -0.1700

Data Index: 7865764 (Open Web Text)

Max Activating Token Index: 906

Text #9

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4416. Min Act: -0.1700

Data Index: 5649567 (Open Web Text)

Max Activating Token Index: 413

Text #10

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4263. Min Act: -0.1700

Data Index: 7184994 (Open Web Text)

Max Activating Token Index: 576

Text #11

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4294. Min Act: -0.1700

Data Index: 5096964 (Open Web Text)

Max Activating Token Index: 369

Text #12

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4308. Min Act: -0.1700

Data Index: 4909420 (Open Web Text)

Max Activating Token Index: 781

Text #13

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4107. Min Act: -0.1700

Data Index: 8013692 (Open Web Text)

Max Activating Token Index: 991

Text #14

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.4056. Min Act: -0.1700

Data Index: 8681343 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.3750. Min Act: -0.1700

Data Index: 8426694 (Open Web Text)

Max Activating Token Index: 998

Text #16

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.3561. Min Act: -0.1700

Data Index: 1175395 (Open Web Text)

Max Activating Token Index: 49

Text #17

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.3874. Min Act: -0.1700

Data Index: 3571397 (Open Web Text)

Max Activating Token Index: 482

Text #18

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.3692. Min Act: -0.1700

Data Index: 5652669 (Open Web Text)

Max Activating Token Index: 414

Text #19

Max Range: 3.5685. Min Range: -3.5685

Max Act: 3.3499. Min Act: -0.1700

Data Index: 7982953 (Open Web Text)

Max Activating Token Index: 505