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

Dataset: Open Web Text

Neuron 363 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: 3.6020. Min Range: -3.6020

Max Act: 3.6017. Min Act: -0.1700

Data Index: 817152 (Open Web Text)

Max Activating Token Index: 957

Text #1

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.6020. Min Act: -0.1700

Data Index: 2816193 (Open Web Text)

Max Activating Token Index: 927

Text #2

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5936. Min Act: -0.1700

Data Index: 6795411 (Open Web Text)

Max Activating Token Index: 939

Text #3

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5704. Min Act: -0.1700

Data Index: 5060680 (Open Web Text)

Max Activating Token Index: 900

Text #4

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5641. Min Act: -0.1700

Data Index: 3444501 (Open Web Text)

Max Activating Token Index: 766

Text #5

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5770. Min Act: -0.1700

Data Index: 66548 (Open Web Text)

Max Activating Token Index: 947

Text #6

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5676. Min Act: -0.1700

Data Index: 4324715 (Open Web Text)

Max Activating Token Index: 986

Text #7

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5526. Min Act: -0.1700

Data Index: 248594 (Open Web Text)

Max Activating Token Index: 999

Text #8

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5515. Min Act: -0.1700

Data Index: 1082008 (Open Web Text)

Max Activating Token Index: 706

Text #9

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5433. Min Act: -0.1700

Data Index: 5854258 (Open Web Text)

Max Activating Token Index: 980

Text #10

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5463. Min Act: -0.1700

Data Index: 2804370 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5467. Min Act: -0.1700

Data Index: 572313 (Open Web Text)

Max Activating Token Index: 767

Text #12

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5409. Min Act: -0.1700

Data Index: 736928 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5508. Min Act: -0.1700

Data Index: 8352032 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5442. Min Act: -0.1700

Data Index: 6747764 (Open Web Text)

Max Activating Token Index: 786

Text #15

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5263. Min Act: -0.1700

Data Index: 4388528 (Open Web Text)

Max Activating Token Index: 969

Text #16

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.4977. Min Act: -0.1700

Data Index: 4747649 (Open Web Text)

Max Activating Token Index: 967

Text #17

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5363. Min Act: -0.1700

Data Index: 5360966 (Open Web Text)

Max Activating Token Index: 979

Text #18

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5233. Min Act: -0.1700

Data Index: 1804152 (Open Web Text)

Max Activating Token Index: 890

Text #19

Max Range: 3.6020. Min Range: -3.6020

Max Act: 3.5373. Min Act: -0.1700

Data Index: 5878928 (Open Web Text)

Max Activating Token Index: 944