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

Dataset: Open Web Text

Neuron 1949 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: 4.3408. Min Range: -4.3408

Max Act: 4.3408. Min Act: -0.1700

Data Index: 2008982 (Open Web Text)

Max Activating Token Index: 685

Text #1

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.1796. Min Act: -0.1700

Data Index: 2511303 (Open Web Text)

Max Activating Token Index: 967

Text #2

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.2070. Min Act: -0.1700

Data Index: 3409952 (Open Web Text)

Max Activating Token Index: 429

Text #3

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.1603. Min Act: -0.1700

Data Index: 1882539 (Open Web Text)

Max Activating Token Index: 256

Text #4

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.1263. Min Act: -0.1700

Data Index: 8247719 (Open Web Text)

Max Activating Token Index: 581

Text #5

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.1529. Min Act: -0.1700

Data Index: 3581690 (Open Web Text)

Max Activating Token Index: 633

Text #6

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0792. Min Act: -0.1700

Data Index: 8811947 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0616. Min Act: -0.1700

Data Index: 4973847 (Open Web Text)

Max Activating Token Index: 100

Text #8

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0551. Min Act: -0.1700

Data Index: 3066972 (Open Web Text)

Max Activating Token Index: 28

Text #9

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0637. Min Act: -0.1700

Data Index: 261884 (Open Web Text)

Max Activating Token Index: 547

Text #10

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.1012. Min Act: -0.1700

Data Index: 3078097 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0470. Min Act: -0.1700

Data Index: 3249394 (Open Web Text)

Max Activating Token Index: 177

Text #12

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0490. Min Act: -0.1700

Data Index: 304916 (Open Web Text)

Max Activating Token Index: 604

Text #13

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0207. Min Act: -0.1700

Data Index: 3057635 (Open Web Text)

Max Activating Token Index: 124

Text #14

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0610. Min Act: -0.1700

Data Index: 2296956 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0189. Min Act: -0.1700

Data Index: 5657555 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0015. Min Act: -0.1700

Data Index: 5778152 (Open Web Text)

Max Activating Token Index: 748

Text #17

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0154. Min Act: -0.1700

Data Index: 3066841 (Open Web Text)

Max Activating Token Index: 81

Text #18

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0389. Min Act: -0.1700

Data Index: 7331132 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 4.3408. Min Range: -4.3408

Max Act: 4.0282. Min Act: -0.1700

Data Index: 7353540 (Open Web Text)

Max Activating Token Index: 87