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

Dataset: Open Web Text

Neuron 765 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: 3.6691. Min Range: -3.6691

Max Act: 3.6691. Min Act: -0.1700

Data Index: 8445891 (Open Web Text)

Max Activating Token Index: 912

Text #1

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.6227. Min Act: -0.1700

Data Index: 638323 (Open Web Text)

Max Activating Token Index: 200

Text #2

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.6078. Min Act: -0.1700

Data Index: 3942789 (Open Web Text)

Max Activating Token Index: 78

Text #3

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.5804. Min Act: -0.1700

Data Index: 5785573 (Open Web Text)

Max Activating Token Index: 184

Text #4

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.5743. Min Act: -0.1700

Data Index: 4732885 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.5591. Min Act: -0.1700

Data Index: 7857504 (Open Web Text)

Max Activating Token Index: 572

Text #6

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.5097. Min Act: -0.1700

Data Index: 5269870 (Open Web Text)

Max Activating Token Index: 910

Text #7

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.5152. Min Act: -0.1700

Data Index: 3942788 (Open Web Text)

Max Activating Token Index: 373

Text #8

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.5100. Min Act: -0.1700

Data Index: 5885815 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4957. Min Act: -0.1700

Data Index: 2651969 (Open Web Text)

Max Activating Token Index: 803

Text #10

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4971. Min Act: -0.1700

Data Index: 3942792 (Open Web Text)

Max Activating Token Index: 442

Text #11

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4861. Min Act: -0.1700

Data Index: 8714666 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4794. Min Act: -0.1700

Data Index: 7620806 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4940. Min Act: -0.1700

Data Index: 2242811 (Open Web Text)

Max Activating Token Index: 250

Text #14

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4943. Min Act: -0.1700

Data Index: 4305166 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4763. Min Act: -0.1700

Data Index: 6145204 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4378. Min Act: -0.1700

Data Index: 2995391 (Open Web Text)

Max Activating Token Index: 437

Text #17

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4247. Min Act: -0.1700

Data Index: 5885822 (Open Web Text)

Max Activating Token Index: 819

Text #18

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4210. Min Act: -0.1700

Data Index: 8451446 (Open Web Text)

Max Activating Token Index: 654

Text #19

Max Range: 3.6691. Min Range: -3.6691

Max Act: 3.4282. Min Act: -0.1700

Data Index: 4263639 (Open Web Text)

Max Activating Token Index: 299