Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 1718 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.6771. Min Act: -0.1700

Data Index: 6977010 (Open Web Text)

Max Activating Token Index: 136

Text #1

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.6458. Min Act: -0.1700

Data Index: 7427183 (Open Web Text)

Max Activating Token Index: 751

Text #2

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.6458. Min Act: -0.1700

Data Index: 6132233 (Open Web Text)

Max Activating Token Index: 466

Text #3

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5675. Min Act: -0.1700

Data Index: 1120757 (Open Web Text)

Max Activating Token Index: 263

Text #4

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5675. Min Act: -0.1700

Data Index: 2535955 (Open Web Text)

Max Activating Token Index: 471

Text #5

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5362. Min Act: -0.1700

Data Index: 6955452 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5205. Min Act: -0.1700

Data Index: 5752611 (Open Web Text)

Max Activating Token Index: 841

Text #7

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5205. Min Act: -0.1700

Data Index: 6014703 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4736. Min Act: -0.1700

Data Index: 3981362 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4892. Min Act: -0.1700

Data Index: 7189030 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4736. Min Act: -0.1700

Data Index: 4114155 (Open Web Text)

Max Activating Token Index: 541

Text #11

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4736. Min Act: -0.1700

Data Index: 2796129 (Open Web Text)

Max Activating Token Index: 424

Text #12

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4579. Min Act: -0.1700

Data Index: 8117080 (Open Web Text)

Max Activating Token Index: 784

Text #13

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4579. Min Act: -0.1700

Data Index: 8581605 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4579. Min Act: -0.1700

Data Index: 3857431 (Open Web Text)

Max Activating Token Index: 127

Text #15

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4265. Min Act: -0.1700

Data Index: 1487763 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4422. Min Act: -0.1700

Data Index: 4701943 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4422. Min Act: -0.1700

Data Index: 2623391 (Open Web Text)

Max Activating Token Index: 683

Text #18

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4422. Min Act: -0.1700

Data Index: 3815063 (Open Web Text)

Max Activating Token Index: 628

Text #19

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4422. Min Act: -0.1700

Data Index: 6453664 (Open Web Text)

Max Activating Token Index: 919