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

Dataset: Open Web Text

Neuron 1759 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: 1.7755. Min Range: -1.7755

Max Act: 1.7755. Min Act: -0.1700

Data Index: 161441 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.7427. Min Act: -0.1700

Data Index: 6819705 (Open Web Text)

Max Activating Token Index: 1007

Text #2

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.7285. Min Act: -0.1700

Data Index: 7856559 (Open Web Text)

Max Activating Token Index: 961

Text #3

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.6516. Min Act: -0.1700

Data Index: 4312867 (Open Web Text)

Max Activating Token Index: 106

Text #4

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.6333. Min Act: -0.1694

Data Index: 726595 (Open Web Text)

Max Activating Token Index: 645

Text #5

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.6238. Min Act: -0.1700

Data Index: 5602169 (Open Web Text)

Max Activating Token Index: 169

Text #6

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.6087. Min Act: -0.1699

Data Index: 4613519 (Open Web Text)

Max Activating Token Index: 150

Text #7

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.6111. Min Act: -0.1700

Data Index: 5310953 (Open Web Text)

Max Activating Token Index: 502

Text #8

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.6231. Min Act: -0.1700

Data Index: 7544552 (Open Web Text)

Max Activating Token Index: 152

Text #9

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.6083. Min Act: -0.1699

Data Index: 4174007 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.6122. Min Act: -0.1700

Data Index: 6119921 (Open Web Text)

Max Activating Token Index: 805

Text #11

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.6194. Min Act: -0.1700

Data Index: 422124 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.6108. Min Act: -0.1700

Data Index: 2630433 (Open Web Text)

Max Activating Token Index: 867

Text #13

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.5906. Min Act: -0.1694

Data Index: 4174006 (Open Web Text)

Max Activating Token Index: 943

Text #14

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.5960. Min Act: -0.1700

Data Index: 4478770 (Open Web Text)

Max Activating Token Index: 905

Text #15

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.5921. Min Act: -0.1699

Data Index: 4391422 (Open Web Text)

Max Activating Token Index: 515

Text #16

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.5851. Min Act: -0.1700

Data Index: 1207435 (Open Web Text)

Max Activating Token Index: 191

Text #17

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.5875. Min Act: -0.1700

Data Index: 1950720 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.5891. Min Act: -0.1700

Data Index: 2742393 (Open Web Text)

Max Activating Token Index: 261

Text #19

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.5980. Min Act: -0.1700

Data Index: 2798279 (Open Web Text)

Max Activating Token Index: 600