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

Dataset: Open Web Text

Neuron 846 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: 3.5870. Min Range: -3.5870

Max Act: 3.5870. Min Act: -0.1700

Data Index: 3564301 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.5870. Min Act: -0.1700

Data Index: 4591255 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.5870. Min Act: -0.1700

Data Index: 7940053 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.5436. Min Act: -0.1700

Data Index: 623901 (Open Web Text)

Max Activating Token Index: 375

Text #4

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.5145. Min Act: -0.1700

Data Index: 2009773 (Open Web Text)

Max Activating Token Index: 1011

Text #5

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.5087. Min Act: -0.1700

Data Index: 6758628 (Open Web Text)

Max Activating Token Index: 812

Text #6

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.4457. Min Act: -0.1700

Data Index: 5227250 (Open Web Text)

Max Activating Token Index: 364

Text #7

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.4376. Min Act: -0.1700

Data Index: 2196348 (Open Web Text)

Max Activating Token Index: 405

Text #8

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.4359. Min Act: -0.1700

Data Index: 5409134 (Open Web Text)

Max Activating Token Index: 391

Text #9

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.4124. Min Act: -0.1700

Data Index: 3734537 (Open Web Text)

Max Activating Token Index: 332

Text #10

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.3888. Min Act: -0.1700

Data Index: 4605206 (Open Web Text)

Max Activating Token Index: 232

Text #11

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.4279. Min Act: -0.1700

Data Index: 7621473 (Open Web Text)

Max Activating Token Index: 709

Text #12

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.4164. Min Act: -0.1700

Data Index: 2912843 (Open Web Text)

Max Activating Token Index: 388

Text #13

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.4122. Min Act: -0.1700

Data Index: 2924852 (Open Web Text)

Max Activating Token Index: 386

Text #14

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.3878. Min Act: -0.1700

Data Index: 5432968 (Open Web Text)

Max Activating Token Index: 225

Text #15

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.3654. Min Act: -0.1700

Data Index: 8221532 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.4209. Min Act: -0.1700

Data Index: 296748 (Open Web Text)

Max Activating Token Index: 903

Text #17

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.3742. Min Act: -0.1700

Data Index: 5146934 (Open Web Text)

Max Activating Token Index: 602

Text #18

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.3612. Min Act: -0.1700

Data Index: 6290636 (Open Web Text)

Max Activating Token Index: 657

Text #19

Max Range: 3.5870. Min Range: -3.5870

Max Act: 3.3616. Min Act: -0.1700

Data Index: 5675102 (Open Web Text)

Max Activating Token Index: 560