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

Dataset: Open Web Text

Neuron 1249 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: 4.4268. Min Range: -4.4268

Max Act: 4.4268. Min Act: -0.1700

Data Index: 8249426 (Open Web Text)

Max Activating Token Index: 994

Text #1

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.3827. Min Act: -0.1700

Data Index: 4645675 (Open Web Text)

Max Activating Token Index: 899

Text #2

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.3640. Min Act: -0.1700

Data Index: 481586 (Open Web Text)

Max Activating Token Index: 743

Text #3

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.3949. Min Act: -0.1700

Data Index: 2945703 (Open Web Text)

Max Activating Token Index: 815

Text #4

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.3306. Min Act: -0.1700

Data Index: 1077650 (Open Web Text)

Max Activating Token Index: 831

Text #5

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.3539. Min Act: -0.1700

Data Index: 8745453 (Open Web Text)

Max Activating Token Index: 793

Text #6

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.3355. Min Act: -0.1700

Data Index: 3813874 (Open Web Text)

Max Activating Token Index: 744

Text #7

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.3098. Min Act: -0.1700

Data Index: 5081543 (Open Web Text)

Max Activating Token Index: 523

Text #8

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.2874. Min Act: -0.1700

Data Index: 28220 (Open Web Text)

Max Activating Token Index: 494

Text #9

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.3002. Min Act: -0.1700

Data Index: 5039916 (Open Web Text)

Max Activating Token Index: 987

Text #10

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.3136. Min Act: -0.1700

Data Index: 3722475 (Open Web Text)

Max Activating Token Index: 571

Text #11

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.2717. Min Act: -0.1700

Data Index: 7240634 (Open Web Text)

Max Activating Token Index: 703

Text #12

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.2489. Min Act: -0.1700

Data Index: 7402450 (Open Web Text)

Max Activating Token Index: 762

Text #13

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.2821. Min Act: -0.1700

Data Index: 467107 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.2612. Min Act: -0.1700

Data Index: 2491288 (Open Web Text)

Max Activating Token Index: 872

Text #15

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.2681. Min Act: -0.1700

Data Index: 6739502 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.2462. Min Act: -0.1700

Data Index: 2101379 (Open Web Text)

Max Activating Token Index: 507

Text #17

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.2527. Min Act: -0.1700

Data Index: 2029261 (Open Web Text)

Max Activating Token Index: 17

Text #18

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.2788. Min Act: -0.1700

Data Index: 3728200 (Open Web Text)

Max Activating Token Index: 58

Text #19

Max Range: 4.4268. Min Range: -4.4268

Max Act: 4.2561. Min Act: -0.1700

Data Index: 1795063 (Open Web Text)

Max Activating Token Index: 150