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

Dataset: Open Web Text

Neuron 1571 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: 3.7327. Min Range: -3.7327

Max Act: 3.7327. Min Act: -0.1700

Data Index: 6205757 (Open Web Text)

Max Activating Token Index: 814

Text #1

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.6782. Min Act: -0.1700

Data Index: 5969206 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.6709. Min Act: -0.1700

Data Index: 8254543 (Open Web Text)

Max Activating Token Index: 100

Text #3

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.6819. Min Act: -0.1700

Data Index: 5192142 (Open Web Text)

Max Activating Token Index: 656

Text #4

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.6138. Min Act: -0.1700

Data Index: 5091276 (Open Web Text)

Max Activating Token Index: 883

Text #5

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5996. Min Act: -0.1700

Data Index: 4685855 (Open Web Text)

Max Activating Token Index: 700

Text #6

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.6060. Min Act: -0.1700

Data Index: 7293139 (Open Web Text)

Max Activating Token Index: 563

Text #7

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5512. Min Act: -0.1700

Data Index: 8205212 (Open Web Text)

Max Activating Token Index: 775

Text #8

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5583. Min Act: -0.1700

Data Index: 3116577 (Open Web Text)

Max Activating Token Index: 687

Text #9

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5499. Min Act: -0.1700

Data Index: 767402 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5539. Min Act: -0.1700

Data Index: 48040 (Open Web Text)

Max Activating Token Index: 825

Text #11

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5487. Min Act: -0.1700

Data Index: 4936988 (Open Web Text)

Max Activating Token Index: 831

Text #12

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5701. Min Act: -0.1700

Data Index: 3290485 (Open Web Text)

Max Activating Token Index: 591

Text #13

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5379. Min Act: -0.1700

Data Index: 1944828 (Open Web Text)

Max Activating Token Index: 39

Text #14

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.4984. Min Act: -0.1700

Data Index: 4679106 (Open Web Text)

Max Activating Token Index: 823

Text #15

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5418. Min Act: -0.1700

Data Index: 3918454 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5258. Min Act: -0.1700

Data Index: 3133774 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5152. Min Act: -0.1700

Data Index: 5305805 (Open Web Text)

Max Activating Token Index: 546

Text #18

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.4953. Min Act: -0.1700

Data Index: 3881893 (Open Web Text)

Max Activating Token Index: 327

Text #19

Max Range: 3.7327. Min Range: -3.7327

Max Act: 3.5031. Min Act: -0.1700

Data Index: 8285184 (Open Web Text)

Max Activating Token Index: 35