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

Dataset: Open Web Text

Neuron 2634 in Layer 4

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: 4.9550. Min Range: -4.9550

Max Act: 4.9550. Min Act: -0.1700

Data Index: 3064592 (Open Web Text)

Max Activating Token Index: 702

Text #1

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.9200. Min Act: -0.1700

Data Index: 4275940 (Open Web Text)

Max Activating Token Index: 992

Text #2

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.8646. Min Act: -0.1700

Data Index: 1322698 (Open Web Text)

Max Activating Token Index: 1009

Text #3

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.8335. Min Act: -0.1700

Data Index: 3606479 (Open Web Text)

Max Activating Token Index: 913

Text #4

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.8389. Min Act: -0.1700

Data Index: 3061287 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.7833. Min Act: -0.1700

Data Index: 4699888 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.7667. Min Act: -0.1700

Data Index: 431861 (Open Web Text)

Max Activating Token Index: 574

Text #7

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.7466. Min Act: -0.1700

Data Index: 2029057 (Open Web Text)

Max Activating Token Index: 1003

Text #8

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.7529. Min Act: -0.1700

Data Index: 6143050 (Open Web Text)

Max Activating Token Index: 994

Text #9

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.7192. Min Act: -0.1700

Data Index: 5698285 (Open Web Text)

Max Activating Token Index: 729

Text #10

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.6913. Min Act: -0.1700

Data Index: 896533 (Open Web Text)

Max Activating Token Index: 864

Text #11

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.6889. Min Act: -0.1700

Data Index: 336961 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.6950. Min Act: -0.1700

Data Index: 1484581 (Open Web Text)

Max Activating Token Index: 129

Text #13

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.6969. Min Act: -0.1700

Data Index: 1231042 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.6704. Min Act: -0.1700

Data Index: 1402387 (Open Web Text)

Max Activating Token Index: 861

Text #15

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.7342. Min Act: -0.1700

Data Index: 2385316 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.6735. Min Act: -0.1700

Data Index: 5427906 (Open Web Text)

Max Activating Token Index: 105

Text #17

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.6594. Min Act: -0.1700

Data Index: 4040859 (Open Web Text)

Max Activating Token Index: 930

Text #18

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.6319. Min Act: -0.1700

Data Index: 2893282 (Open Web Text)

Max Activating Token Index: 733

Text #19

Max Range: 4.9550. Min Range: -4.9550

Max Act: 4.6477. Min Act: -0.1700

Data Index: 1402383 (Open Web Text)

Max Activating Token Index: 513