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

Dataset: Open Web Text

Neuron 963 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: 5.1348. Min Range: -5.1348

Max Act: 5.1348. Min Act: -0.1700

Data Index: 3181163 (Open Web Text)

Max Activating Token Index: 904

Text #1

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.9481. Min Act: -0.1700

Data Index: 4278307 (Open Web Text)

Max Activating Token Index: 56

Text #2

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.8581. Min Act: -0.1700

Data Index: 8539147 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.8322. Min Act: -0.1700

Data Index: 4030729 (Open Web Text)

Max Activating Token Index: 853

Text #4

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.7588. Min Act: -0.1700

Data Index: 3516042 (Open Web Text)

Max Activating Token Index: 621

Text #5

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.7236. Min Act: -0.1700

Data Index: 7798717 (Open Web Text)

Max Activating Token Index: 534

Text #6

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.7044. Min Act: -0.1700

Data Index: 3698927 (Open Web Text)

Max Activating Token Index: 730

Text #7

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.7495. Min Act: -0.1700

Data Index: 2328284 (Open Web Text)

Max Activating Token Index: 796

Text #8

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6966. Min Act: -0.1700

Data Index: 1051261 (Open Web Text)

Max Activating Token Index: 361

Text #9

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6791. Min Act: -0.1700

Data Index: 3787917 (Open Web Text)

Max Activating Token Index: 833

Text #10

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.7122. Min Act: -0.1700

Data Index: 807543 (Open Web Text)

Max Activating Token Index: 206

Text #11

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6720. Min Act: -0.1700

Data Index: 1798267 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6721. Min Act: -0.1700

Data Index: 4421880 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6805. Min Act: -0.1700

Data Index: 2357392 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6592. Min Act: -0.1700

Data Index: 7859847 (Open Web Text)

Max Activating Token Index: 881

Text #15

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6567. Min Act: -0.1700

Data Index: 4138763 (Open Web Text)

Max Activating Token Index: 741

Text #16

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6643. Min Act: -0.1700

Data Index: 4591867 (Open Web Text)

Max Activating Token Index: 778

Text #17

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6596. Min Act: -0.1700

Data Index: 7525172 (Open Web Text)

Max Activating Token Index: 627

Text #18

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6440. Min Act: -0.1700

Data Index: 6979505 (Open Web Text)

Max Activating Token Index: 545

Text #19

Max Range: 5.1348. Min Range: -5.1348

Max Act: 4.6371. Min Act: -0.1700

Data Index: 5677471 (Open Web Text)

Max Activating Token Index: 793