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

Dataset: Open Web Text

Neuron 1412 in Layer 5

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: 4.3719. Min Range: -4.3719

Max Act: 4.3719. Min Act: -0.1700

Data Index: 5887950 (Open Web Text)

Max Activating Token Index: 607

Text #1

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.3479. Min Act: -0.1700

Data Index: 3591325 (Open Web Text)

Max Activating Token Index: 550

Text #2

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2995. Min Act: -0.1700

Data Index: 1684927 (Open Web Text)

Max Activating Token Index: 811

Text #3

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.3093. Min Act: -0.1700

Data Index: 8149162 (Open Web Text)

Max Activating Token Index: 332

Text #4

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.3315. Min Act: -0.1700

Data Index: 4920980 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2920. Min Act: -0.1700

Data Index: 554137 (Open Web Text)

Max Activating Token Index: 245

Text #6

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2646. Min Act: -0.1700

Data Index: 8004650 (Open Web Text)

Max Activating Token Index: 473

Text #7

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2834. Min Act: -0.1700

Data Index: 7182900 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2577. Min Act: -0.1700

Data Index: 1428642 (Open Web Text)

Max Activating Token Index: 349

Text #9

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2648. Min Act: -0.1700

Data Index: 6958419 (Open Web Text)

Max Activating Token Index: 643

Text #10

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.1872. Min Act: -0.1700

Data Index: 6734107 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.1928. Min Act: -0.1700

Data Index: 835595 (Open Web Text)

Max Activating Token Index: 539

Text #12

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2294. Min Act: -0.1700

Data Index: 5869914 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2270. Min Act: -0.1700

Data Index: 5548856 (Open Web Text)

Max Activating Token Index: 895

Text #14

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2377. Min Act: -0.1700

Data Index: 7494965 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2109. Min Act: -0.1700

Data Index: 4412824 (Open Web Text)

Max Activating Token Index: 743

Text #16

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2231. Min Act: -0.1700

Data Index: 7993086 (Open Web Text)

Max Activating Token Index: 900

Text #17

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.2357. Min Act: -0.1700

Data Index: 6370527 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.1774. Min Act: -0.1700

Data Index: 1458061 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 4.3719. Min Range: -4.3719

Max Act: 4.1919. Min Act: -0.1700

Data Index: 1086638 (Open Web Text)

Max Activating Token Index: 243