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

Dataset: Open Web Text

Neuron 842 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: 4.5813. Min Range: -4.5813

Max Act: 4.3705. Min Act: -0.1700

Data Index: 6603274 (Open Web Text)

Max Activating Token Index: 422

Text #1

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.5813. Min Act: -0.1700

Data Index: 5832443 (Open Web Text)

Max Activating Token Index: 761

Text #2

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.5108. Min Act: -0.1700

Data Index: 4478810 (Open Web Text)

Max Activating Token Index: 219

Text #3

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.4663. Min Act: -0.1700

Data Index: 3116947 (Open Web Text)

Max Activating Token Index: 221

Text #4

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.3070. Min Act: -0.1700

Data Index: 1115667 (Open Web Text)

Max Activating Token Index: 735

Text #5

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.2919. Min Act: -0.1700

Data Index: 8741392 (Open Web Text)

Max Activating Token Index: 218

Text #6

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.2486. Min Act: -0.1700

Data Index: 187288 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.3318. Min Act: -0.1700

Data Index: 2743385 (Open Web Text)

Max Activating Token Index: 422

Text #8

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.0600. Min Act: -0.1700

Data Index: 3242779 (Open Web Text)

Max Activating Token Index: 364

Text #9

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.2448. Min Act: -0.1700

Data Index: 8397707 (Open Web Text)

Max Activating Token Index: 693

Text #10

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.2469. Min Act: -0.1700

Data Index: 3083374 (Open Web Text)

Max Activating Token Index: 595

Text #11

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.1717. Min Act: -0.1700

Data Index: 5423980 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.1840. Min Act: -0.1700

Data Index: 5205342 (Open Web Text)

Max Activating Token Index: 1004

Text #13

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.1895. Min Act: -0.1700

Data Index: 4448466 (Open Web Text)

Max Activating Token Index: 95

Text #14

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.2101. Min Act: -0.1700

Data Index: 5732932 (Open Web Text)

Max Activating Token Index: 683

Text #15

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.1619. Min Act: -0.1700

Data Index: 8508970 (Open Web Text)

Max Activating Token Index: 915

Text #16

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.2391. Min Act: -0.1700

Data Index: 7324614 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.1489. Min Act: -0.1700

Data Index: 7849039 (Open Web Text)

Max Activating Token Index: 683

Text #18

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.2113. Min Act: -0.1700

Data Index: 8370664 (Open Web Text)

Max Activating Token Index: 422

Text #19

Max Range: 4.5813. Min Range: -4.5813

Max Act: 4.1291. Min Act: -0.1700

Data Index: 1301842 (Open Web Text)

Max Activating Token Index: 131