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

Dataset: Open Web Text

Neuron 2577 in Layer 6

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: 4.5495. Min Range: -4.5495

Max Act: 4.5495. Min Act: -0.1700

Data Index: 6625271 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4553. Min Act: -0.1700

Data Index: 2831706 (Open Web Text)

Max Activating Token Index: 301

Text #2

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4351. Min Act: -0.1700

Data Index: 8197093 (Open Web Text)

Max Activating Token Index: 774

Text #3

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3734. Min Act: -0.1700

Data Index: 1787529 (Open Web Text)

Max Activating Token Index: 145

Text #4

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3596. Min Act: -0.1700

Data Index: 2942446 (Open Web Text)

Max Activating Token Index: 174

Text #5

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3718. Min Act: -0.1700

Data Index: 2293988 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3668. Min Act: -0.1700

Data Index: 1146411 (Open Web Text)

Max Activating Token Index: 449

Text #7

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3586. Min Act: -0.1700

Data Index: 5121560 (Open Web Text)

Max Activating Token Index: 606

Text #8

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3659. Min Act: -0.1700

Data Index: 3776871 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3472. Min Act: -0.1700

Data Index: 7758564 (Open Web Text)

Max Activating Token Index: 787

Text #10

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3146. Min Act: -0.1700

Data Index: 5071736 (Open Web Text)

Max Activating Token Index: 548

Text #11

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3394. Min Act: -0.1700

Data Index: 4601572 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.2879. Min Act: -0.1700

Data Index: 5081086 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3147. Min Act: -0.1700

Data Index: 5033718 (Open Web Text)

Max Activating Token Index: 220

Text #14

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.2774. Min Act: -0.1700

Data Index: 6519184 (Open Web Text)

Max Activating Token Index: 661

Text #15

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.2937. Min Act: -0.1700

Data Index: 6184463 (Open Web Text)

Max Activating Token Index: 329

Text #16

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.2982. Min Act: -0.1700

Data Index: 1452968 (Open Web Text)

Max Activating Token Index: 719

Text #17

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.2836. Min Act: -0.1700

Data Index: 1438255 (Open Web Text)

Max Activating Token Index: 543

Text #18

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.2981. Min Act: -0.1700

Data Index: 3817601 (Open Web Text)

Max Activating Token Index: 606

Text #19

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.2921. Min Act: -0.1700

Data Index: 5606436 (Open Web Text)

Max Activating Token Index: 27