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

Dataset: Open Web Text

Neuron 2951 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: 3.5474. Min Range: -3.5474

Max Act: 3.5474. Min Act: -0.1700

Data Index: 1891042 (Open Web Text)

Max Activating Token Index: 304

Text #1

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.5267. Min Act: -0.1700

Data Index: 7106333 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.4896. Min Act: -0.1700

Data Index: 341105 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.4783. Min Act: -0.1700

Data Index: 1464997 (Open Web Text)

Max Activating Token Index: 859

Text #4

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.4717. Min Act: -0.1700

Data Index: 7335713 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.4774. Min Act: -0.1700

Data Index: 7884497 (Open Web Text)

Max Activating Token Index: 875

Text #6

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.4368. Min Act: -0.1700

Data Index: 7884498 (Open Web Text)

Max Activating Token Index: 90

Text #7

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.4027. Min Act: -0.1700

Data Index: 8183886 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.4194. Min Act: -0.1700

Data Index: 193112 (Open Web Text)

Max Activating Token Index: 246

Text #9

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.4124. Min Act: -0.1700

Data Index: 3351614 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.3784. Min Act: -0.1700

Data Index: 6761371 (Open Web Text)

Max Activating Token Index: 855

Text #11

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.3717. Min Act: -0.1700

Data Index: 4477165 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.3738. Min Act: -0.1700

Data Index: 1139255 (Open Web Text)

Max Activating Token Index: 574

Text #13

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.3470. Min Act: -0.1700

Data Index: 2883113 (Open Web Text)

Max Activating Token Index: 522

Text #14

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.3754. Min Act: -0.1700

Data Index: 7615372 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.3834. Min Act: -0.1700

Data Index: 5954406 (Open Web Text)

Max Activating Token Index: 781

Text #16

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.3694. Min Act: -0.1700

Data Index: 5933726 (Open Web Text)

Max Activating Token Index: 820

Text #17

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.3923. Min Act: -0.1700

Data Index: 7079688 (Open Web Text)

Max Activating Token Index: 135

Text #18

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.3837. Min Act: -0.1700

Data Index: 1456174 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 3.5474. Min Range: -3.5474

Max Act: 3.3681. Min Act: -0.1700

Data Index: 2708505 (Open Web Text)

Max Activating Token Index: 323