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

Dataset: Open Web Text

Neuron 1411 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: 3.7805. Min Range: -3.7805

Max Act: 3.7805. Min Act: -0.1700

Data Index: 8806651 (Open Web Text)

Max Activating Token Index: 941

Text #1

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.6914. Min Act: -0.1700

Data Index: 3975848 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.6742. Min Act: -0.1700

Data Index: 231859 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.6610. Min Act: -0.1700

Data Index: 2872171 (Open Web Text)

Max Activating Token Index: 835

Text #4

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.5850. Min Act: -0.1700

Data Index: 7175734 (Open Web Text)

Max Activating Token Index: 67

Text #5

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.5446. Min Act: -0.1700

Data Index: 6315434 (Open Web Text)

Max Activating Token Index: 55

Text #6

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.5137. Min Act: -0.1700

Data Index: 3978142 (Open Web Text)

Max Activating Token Index: 288

Text #7

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.5458. Min Act: -0.1700

Data Index: 4973737 (Open Web Text)

Max Activating Token Index: 80

Text #8

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4970. Min Act: -0.1700

Data Index: 7069184 (Open Web Text)

Max Activating Token Index: 462

Text #9

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4655. Min Act: -0.1700

Data Index: 570173 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.5010. Min Act: -0.1700

Data Index: 6773602 (Open Web Text)

Max Activating Token Index: 89

Text #11

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4948. Min Act: -0.1700

Data Index: 5233695 (Open Web Text)

Max Activating Token Index: 104

Text #12

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4862. Min Act: -0.1700

Data Index: 2259204 (Open Web Text)

Max Activating Token Index: 527

Text #13

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4457. Min Act: -0.1700

Data Index: 4214659 (Open Web Text)

Max Activating Token Index: 540

Text #14

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4401. Min Act: -0.1700

Data Index: 6804053 (Open Web Text)

Max Activating Token Index: 115

Text #15

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4671. Min Act: -0.1700

Data Index: 231858 (Open Web Text)

Max Activating Token Index: 353

Text #16

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4283. Min Act: -0.1700

Data Index: 6381160 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4287. Min Act: -0.1700

Data Index: 2312994 (Open Web Text)

Max Activating Token Index: 80

Text #18

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.4041. Min Act: -0.1700

Data Index: 3201796 (Open Web Text)

Max Activating Token Index: 543

Text #19

Max Range: 3.7805. Min Range: -3.7805

Max Act: 3.3785. Min Act: -0.1700

Data Index: 5080256 (Open Web Text)

Max Activating Token Index: 428