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

Dataset: Open Web Text

Neuron 53 in Layer 3

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: 2.5294. Min Range: -2.5294

Max Act: 2.5294. Min Act: -0.1700

Data Index: 269587 (Open Web Text)

Max Activating Token Index: 759

Text #1

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4789. Min Act: -0.1700

Data Index: 7466871 (Open Web Text)

Max Activating Token Index: 866

Text #2

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4308. Min Act: -0.1700

Data Index: 6758299 (Open Web Text)

Max Activating Token Index: 1003

Text #3

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4286. Min Act: -0.1700

Data Index: 564021 (Open Web Text)

Max Activating Token Index: 242

Text #4

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4226. Min Act: -0.1700

Data Index: 3054751 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4312. Min Act: -0.1700

Data Index: 5958818 (Open Web Text)

Max Activating Token Index: 430

Text #6

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4290. Min Act: -0.1700

Data Index: 2765990 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4090. Min Act: -0.1700

Data Index: 6007584 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4176. Min Act: -0.1700

Data Index: 4299702 (Open Web Text)

Max Activating Token Index: 522

Text #9

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4008. Min Act: -0.1700

Data Index: 7878580 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4108. Min Act: -0.1700

Data Index: 2544613 (Open Web Text)

Max Activating Token Index: 522

Text #11

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.3800. Min Act: -0.1700

Data Index: 1983881 (Open Web Text)

Max Activating Token Index: 910

Text #12

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.4019. Min Act: -0.1700

Data Index: 4576338 (Open Web Text)

Max Activating Token Index: 719

Text #13

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.3955. Min Act: -0.1700

Data Index: 1082022 (Open Web Text)

Max Activating Token Index: 546

Text #14

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.3670. Min Act: -0.1700

Data Index: 7889780 (Open Web Text)

Max Activating Token Index: 657

Text #15

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.3817. Min Act: -0.1700

Data Index: 6423390 (Open Web Text)

Max Activating Token Index: 498

Text #16

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.3656. Min Act: -0.1700

Data Index: 5000595 (Open Web Text)

Max Activating Token Index: 539

Text #17

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.3607. Min Act: -0.1700

Data Index: 5848383 (Open Web Text)

Max Activating Token Index: 918

Text #18

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.3629. Min Act: -0.1700

Data Index: 2184440 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.5294. Min Range: -2.5294

Max Act: 2.3575. Min Act: -0.1700

Data Index: 3351753 (Open Web Text)

Max Activating Token Index: 755