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

Dataset: Open Web Text

Neuron 378 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: 5.3678. Min Range: -5.3678

Max Act: 5.3678. Min Act: -0.1700

Data Index: 5801182 (Open Web Text)

Max Activating Token Index: 241

Text #1

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.2761. Min Act: -0.1700

Data Index: 5903048 (Open Web Text)

Max Activating Token Index: 553

Text #2

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.1926. Min Act: -0.1700

Data Index: 1481717 (Open Web Text)

Max Activating Token Index: 327

Text #3

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.1842. Min Act: -0.1700

Data Index: 6462866 (Open Web Text)

Max Activating Token Index: 44

Text #4

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.1763. Min Act: -0.1700

Data Index: 8678188 (Open Web Text)

Max Activating Token Index: 673

Text #5

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.1506. Min Act: -0.1700

Data Index: 2460858 (Open Web Text)

Max Activating Token Index: 611

Text #6

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.1446. Min Act: -0.1698

Data Index: 4413718 (Open Web Text)

Max Activating Token Index: 930

Text #7

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.1173. Min Act: -0.1700

Data Index: 1528049 (Open Web Text)

Max Activating Token Index: 319

Text #8

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0857. Min Act: -0.1700

Data Index: 2431192 (Open Web Text)

Max Activating Token Index: 126

Text #9

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0568. Min Act: -0.1700

Data Index: 4800142 (Open Web Text)

Max Activating Token Index: 229

Text #10

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0783. Min Act: -0.1700

Data Index: 5385463 (Open Web Text)

Max Activating Token Index: 168

Text #11

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0833. Min Act: -0.1700

Data Index: 1088552 (Open Web Text)

Max Activating Token Index: 728

Text #12

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0825. Min Act: -0.1700

Data Index: 7177949 (Open Web Text)

Max Activating Token Index: 623

Text #13

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0932. Min Act: -0.1700

Data Index: 4258276 (Open Web Text)

Max Activating Token Index: 496

Text #14

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0862. Min Act: -0.1700

Data Index: 3892277 (Open Web Text)

Max Activating Token Index: 612

Text #15

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0711. Min Act: -0.1700

Data Index: 7904676 (Open Web Text)

Max Activating Token Index: 458

Text #16

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0363. Min Act: -0.1700

Data Index: 8654457 (Open Web Text)

Max Activating Token Index: 364

Text #17

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0481. Min Act: -0.1700

Data Index: 1550245 (Open Web Text)

Max Activating Token Index: 386

Text #18

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0236. Min Act: -0.1700

Data Index: 1645566 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 5.3678. Min Range: -5.3678

Max Act: 5.0091. Min Act: -0.1700

Data Index: 4362569 (Open Web Text)

Max Activating Token Index: 192