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

Dataset: Open Web Text

Neuron 2010 in Layer 5

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: 3.1362. Min Range: -3.1362

Max Act: 3.1362. Min Act: -0.1700

Data Index: 4235594 (Open Web Text)

Max Activating Token Index: 531

Text #1

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0517. Min Act: -0.1700

Data Index: 3965966 (Open Web Text)

Max Activating Token Index: 395

Text #2

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.9741. Min Act: -0.1700

Data Index: 4480367 (Open Web Text)

Max Activating Token Index: 86

Text #3

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.9960. Min Act: -0.1700

Data Index: 2775622 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.8909. Min Act: -0.1700

Data Index: 2462199 (Open Web Text)

Max Activating Token Index: 553

Text #5

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.8746. Min Act: -0.1700

Data Index: 1053196 (Open Web Text)

Max Activating Token Index: 665

Text #6

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.8581. Min Act: -0.1700

Data Index: 2285577 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.8499. Min Act: -0.1700

Data Index: 332720 (Open Web Text)

Max Activating Token Index: 373

Text #8

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.8055. Min Act: -0.1700

Data Index: 6459495 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.8320. Min Act: -0.1700

Data Index: 4437536 (Open Web Text)

Max Activating Token Index: 59

Text #10

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.8161. Min Act: -0.1700

Data Index: 5925783 (Open Web Text)

Max Activating Token Index: 400

Text #11

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.7894. Min Act: -0.1700

Data Index: 6416223 (Open Web Text)

Max Activating Token Index: 412

Text #12

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.7805. Min Act: -0.1700

Data Index: 6762827 (Open Web Text)

Max Activating Token Index: 210

Text #13

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.7998. Min Act: -0.1700

Data Index: 1538787 (Open Web Text)

Max Activating Token Index: 295

Text #14

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.7816. Min Act: -0.1700

Data Index: 7890709 (Open Web Text)

Max Activating Token Index: 557

Text #15

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.7826. Min Act: -0.1700

Data Index: 408676 (Open Web Text)

Max Activating Token Index: 177

Text #16

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.7825. Min Act: -0.1700

Data Index: 3731792 (Open Web Text)

Max Activating Token Index: 183

Text #17

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.7784. Min Act: -0.1700

Data Index: 2964197 (Open Web Text)

Max Activating Token Index: 928

Text #18

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.7882. Min Act: -0.1700

Data Index: 5644327 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.7652. Min Act: -0.1700

Data Index: 7167999 (Open Web Text)

Max Activating Token Index: 977