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

Dataset: Open Web Text

Neuron 2513 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: 4.6783. Min Range: -4.6783

Max Act: 4.6783. Min Act: -0.1700

Data Index: 7726058 (Open Web Text)

Max Activating Token Index: 563

Text #1

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.6072. Min Act: -0.1700

Data Index: 6067351 (Open Web Text)

Max Activating Token Index: 52

Text #2

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.5512. Min Act: -0.1700

Data Index: 7382658 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.5393. Min Act: -0.1700

Data Index: 6246541 (Open Web Text)

Max Activating Token Index: 938

Text #4

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.5369. Min Act: -0.1700

Data Index: 266011 (Open Web Text)

Max Activating Token Index: 322

Text #5

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.5489. Min Act: -0.1700

Data Index: 5887928 (Open Web Text)

Max Activating Token Index: 342

Text #6

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.5267. Min Act: -0.1700

Data Index: 1873774 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.5101. Min Act: -0.1700

Data Index: 7432764 (Open Web Text)

Max Activating Token Index: 495

Text #8

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4337. Min Act: -0.1700

Data Index: 3950852 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4337. Min Act: -0.1700

Data Index: 7051120 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4096. Min Act: -0.1700

Data Index: 3288693 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4337. Min Act: -0.1700

Data Index: 3300245 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4337. Min Act: -0.1700

Data Index: 6494615 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4342. Min Act: -0.1700

Data Index: 4325822 (Open Web Text)

Max Activating Token Index: 555

Text #14

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4337. Min Act: -0.1700

Data Index: 4853362 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4096. Min Act: -0.1700

Data Index: 2816109 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4041. Min Act: -0.1700

Data Index: 1707726 (Open Web Text)

Max Activating Token Index: 807

Text #17

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4100. Min Act: -0.1700

Data Index: 6812296 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4100. Min Act: -0.1700

Data Index: 2857017 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.6783. Min Range: -4.6783

Max Act: 4.4106. Min Act: -0.1700

Data Index: 3476728 (Open Web Text)

Max Activating Token Index: 365