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

Dataset: Open Web Text

Neuron 2228 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: 1.8144. Min Range: -1.8144

Max Act: 1.8020. Min Act: -0.1700

Data Index: 2620522 (Open Web Text)

Max Activating Token Index: 991

Text #1

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.8144. Min Act: -0.1700

Data Index: 1197480 (Open Web Text)

Max Activating Token Index: 872

Text #2

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.8097. Min Act: -0.1700

Data Index: 6527126 (Open Web Text)

Max Activating Token Index: 64

Text #3

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.8030. Min Act: -0.1700

Data Index: 8496676 (Open Web Text)

Max Activating Token Index: 350

Text #4

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7917. Min Act: -0.1700

Data Index: 21973 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7881. Min Act: -0.1700

Data Index: 4948658 (Open Web Text)

Max Activating Token Index: 658

Text #6

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7792. Min Act: -0.1700

Data Index: 8626142 (Open Web Text)

Max Activating Token Index: 730

Text #7

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7911. Min Act: -0.1700

Data Index: 555074 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7949. Min Act: -0.1700

Data Index: 1589927 (Open Web Text)

Max Activating Token Index: 510

Text #9

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7833. Min Act: -0.1700

Data Index: 5183526 (Open Web Text)

Max Activating Token Index: 288

Text #10

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7648. Min Act: -0.1700

Data Index: 7390795 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7727. Min Act: -0.1700

Data Index: 6596220 (Open Web Text)

Max Activating Token Index: 946

Text #12

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7768. Min Act: -0.1700

Data Index: 8738730 (Open Web Text)

Max Activating Token Index: 61

Text #13

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7680. Min Act: -0.1700

Data Index: 6647288 (Open Web Text)

Max Activating Token Index: 168

Text #14

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7640. Min Act: -0.1700

Data Index: 2750745 (Open Web Text)

Max Activating Token Index: 211

Text #15

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7688. Min Act: -0.1700

Data Index: 6664573 (Open Web Text)

Max Activating Token Index: 255

Text #16

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7621. Min Act: -0.1700

Data Index: 6124890 (Open Web Text)

Max Activating Token Index: 150

Text #17

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7667. Min Act: -0.1700

Data Index: 7357659 (Open Web Text)

Max Activating Token Index: 56

Text #18

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7666. Min Act: -0.1700

Data Index: 4214591 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.7622. Min Act: -0.1700

Data Index: 2533929 (Open Web Text)

Max Activating Token Index: 268