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

Dataset: Open Web Text

Neuron 1492 in Layer 2

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: 3.8654. Min Range: -3.8654

Max Act: 3.8654. Min Act: -0.1700

Data Index: 3061826 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.7996. Min Act: -0.1700

Data Index: 4532435 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.8057. Min Act: -0.1700

Data Index: 5158484 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.7463. Min Act: -0.1700

Data Index: 3615189 (Open Web Text)

Max Activating Token Index: 869

Text #4

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.7377. Min Act: -0.1700

Data Index: 5487839 (Open Web Text)

Max Activating Token Index: 895

Text #5

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.7363. Min Act: -0.1700

Data Index: 8188316 (Open Web Text)

Max Activating Token Index: 411

Text #6

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.7186. Min Act: -0.1700

Data Index: 910551 (Open Web Text)

Max Activating Token Index: 406

Text #7

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.7484. Min Act: -0.1700

Data Index: 5227732 (Open Web Text)

Max Activating Token Index: 518

Text #8

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6871. Min Act: -0.1700

Data Index: 6719581 (Open Web Text)

Max Activating Token Index: 425

Text #9

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.7038. Min Act: -0.1700

Data Index: 8302394 (Open Web Text)

Max Activating Token Index: 123

Text #10

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6899. Min Act: -0.1700

Data Index: 7761704 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6968. Min Act: -0.1700

Data Index: 2869301 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6930. Min Act: -0.1700

Data Index: 8472779 (Open Web Text)

Max Activating Token Index: 346

Text #13

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6735. Min Act: -0.1700

Data Index: 1510529 (Open Web Text)

Max Activating Token Index: 148

Text #14

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6661. Min Act: -0.1700

Data Index: 7285573 (Open Web Text)

Max Activating Token Index: 551

Text #15

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6791. Min Act: -0.1700

Data Index: 617008 (Open Web Text)

Max Activating Token Index: 752

Text #16

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6838. Min Act: -0.1700

Data Index: 5380188 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6553. Min Act: -0.1700

Data Index: 2360297 (Open Web Text)

Max Activating Token Index: 433

Text #18

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6793. Min Act: -0.1700

Data Index: 5722626 (Open Web Text)

Max Activating Token Index: 464

Text #19

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6639. Min Act: -0.1700

Data Index: 3524359 (Open Web Text)

Max Activating Token Index: 468