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

Dataset: Open Web Text

Neuron 484 in Layer 3

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: 5.3495. Min Range: -5.3495

Max Act: 5.3495. Min Act: -0.1700

Data Index: 5881128 (Open Web Text)

Max Activating Token Index: 710

Text #1

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.2744. Min Act: -0.1700

Data Index: 8737735 (Open Web Text)

Max Activating Token Index: 599

Text #2

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.1808. Min Act: -0.1700

Data Index: 4758819 (Open Web Text)

Max Activating Token Index: 525

Text #3

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.1436. Min Act: -0.1700

Data Index: 2247808 (Open Web Text)

Max Activating Token Index: 110

Text #4

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.1208. Min Act: -0.1700

Data Index: 699531 (Open Web Text)

Max Activating Token Index: 284

Text #5

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.1030. Min Act: -0.1700

Data Index: 4690798 (Open Web Text)

Max Activating Token Index: 523

Text #6

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.1028. Min Act: -0.1700

Data Index: 2166407 (Open Web Text)

Max Activating Token Index: 774

Text #7

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0790. Min Act: -0.1700

Data Index: 8006678 (Open Web Text)

Max Activating Token Index: 485

Text #8

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0985. Min Act: -0.1700

Data Index: 7887656 (Open Web Text)

Max Activating Token Index: 88

Text #9

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.1490. Min Act: -0.1700

Data Index: 4423527 (Open Web Text)

Max Activating Token Index: 810

Text #10

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.1294. Min Act: -0.1700

Data Index: 4737116 (Open Web Text)

Max Activating Token Index: 324

Text #11

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0476. Min Act: -0.1700

Data Index: 1868197 (Open Web Text)

Max Activating Token Index: 81

Text #12

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0609. Min Act: -0.1700

Data Index: 184044 (Open Web Text)

Max Activating Token Index: 883

Text #13

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0297. Min Act: -0.1700

Data Index: 3446063 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0429. Min Act: -0.1700

Data Index: 2259571 (Open Web Text)

Max Activating Token Index: 775

Text #15

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0809. Min Act: -0.1700

Data Index: 8632025 (Open Web Text)

Max Activating Token Index: 487

Text #16

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0588. Min Act: -0.1700

Data Index: 8070761 (Open Web Text)

Max Activating Token Index: 101

Text #17

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0418. Min Act: -0.1700

Data Index: 6297519 (Open Web Text)

Max Activating Token Index: 767

Text #18

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0479. Min Act: -0.1700

Data Index: 6662968 (Open Web Text)

Max Activating Token Index: 829

Text #19

Max Range: 5.3495. Min Range: -5.3495

Max Act: 5.0493. Min Act: -0.1700

Data Index: 809776 (Open Web Text)

Max Activating Token Index: 708