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

Dataset: Open Web Text

Neuron 1525 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: 4.4733. Min Range: -4.4733

Max Act: 4.4733. Min Act: -0.1700

Data Index: 8188219 (Open Web Text)

Max Activating Token Index: 377

Text #1

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.4357. Min Act: -0.1700

Data Index: 1508019 (Open Web Text)

Max Activating Token Index: 408

Text #2

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3552. Min Act: -0.1700

Data Index: 5012200 (Open Web Text)

Max Activating Token Index: 295

Text #3

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3721. Min Act: -0.1700

Data Index: 1704972 (Open Web Text)

Max Activating Token Index: 717

Text #4

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.4068. Min Act: -0.1700

Data Index: 1160463 (Open Web Text)

Max Activating Token Index: 796

Text #5

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3170. Min Act: -0.1700

Data Index: 3770964 (Open Web Text)

Max Activating Token Index: 895

Text #6

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3878. Min Act: -0.1700

Data Index: 6057489 (Open Web Text)

Max Activating Token Index: 473

Text #7

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3306. Min Act: -0.1700

Data Index: 2755633 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3782. Min Act: -0.1700

Data Index: 673381 (Open Web Text)

Max Activating Token Index: 941

Text #9

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3454. Min Act: -0.1700

Data Index: 3653223 (Open Web Text)

Max Activating Token Index: 44

Text #10

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.4003. Min Act: -0.1700

Data Index: 504489 (Open Web Text)

Max Activating Token Index: 948

Text #11

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3004. Min Act: -0.1700

Data Index: 4573521 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3275. Min Act: -0.1700

Data Index: 1985097 (Open Web Text)

Max Activating Token Index: 616

Text #13

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3625. Min Act: -0.1700

Data Index: 493294 (Open Web Text)

Max Activating Token Index: 766

Text #14

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3330. Min Act: -0.1700

Data Index: 6547710 (Open Web Text)

Max Activating Token Index: 370

Text #15

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3085. Min Act: -0.1700

Data Index: 7217843 (Open Web Text)

Max Activating Token Index: 742

Text #16

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3772. Min Act: -0.1700

Data Index: 2979924 (Open Web Text)

Max Activating Token Index: 943

Text #17

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3970. Min Act: -0.1700

Data Index: 1408767 (Open Web Text)

Max Activating Token Index: 457

Text #18

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.3532. Min Act: -0.1700

Data Index: 4672085 (Open Web Text)

Max Activating Token Index: 625

Text #19

Max Range: 4.4733. Min Range: -4.4733

Max Act: 4.2564. Min Act: -0.1700

Data Index: 7192044 (Open Web Text)

Max Activating Token Index: 848