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

Dataset: Open Web Text

Neuron 895 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: 0.4516. Min Range: -0.4516

Max Act: 0.4333. Min Act: -0.1700

Data Index: 1694120 (Open Web Text)

Max Activating Token Index: 466

Text #1

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4428. Min Act: -0.1700

Data Index: 3368907 (Open Web Text)

Max Activating Token Index: 624

Text #2

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4338. Min Act: -0.1700

Data Index: 4481323 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4078. Min Act: -0.1700

Data Index: 6603879 (Open Web Text)

Max Activating Token Index: 521

Text #4

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4516. Min Act: -0.1700

Data Index: 2309879 (Open Web Text)

Max Activating Token Index: 593

Text #5

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4048. Min Act: -0.1700

Data Index: 10014 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3922. Min Act: -0.1700

Data Index: 7253638 (Open Web Text)

Max Activating Token Index: 482

Text #7

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4099. Min Act: -0.1700

Data Index: 6210045 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4300. Min Act: -0.1700

Data Index: 114288 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3956. Min Act: -0.1700

Data Index: 2393773 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.4476. Min Act: -0.1700

Data Index: 2166802 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3866. Min Act: -0.1700

Data Index: 2675043 (Open Web Text)

Max Activating Token Index: 659

Text #12

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3810. Min Act: -0.1700

Data Index: 8087463 (Open Web Text)

Max Activating Token Index: 566

Text #13

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3985. Min Act: -0.1700

Data Index: 4317886 (Open Web Text)

Max Activating Token Index: 597

Text #14

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3896. Min Act: -0.1700

Data Index: 1011391 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3871. Min Act: -0.1700

Data Index: 7365041 (Open Web Text)

Max Activating Token Index: 663

Text #16

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3496. Min Act: -0.1700

Data Index: 7474395 (Open Web Text)

Max Activating Token Index: 666

Text #17

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3893. Min Act: -0.1700

Data Index: 6805656 (Open Web Text)

Max Activating Token Index: 677

Text #18

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3426. Min Act: -0.1700

Data Index: 6761247 (Open Web Text)

Max Activating Token Index: 790

Text #19

Max Range: 0.4516. Min Range: -0.4516

Max Act: 0.3755. Min Act: -0.1700

Data Index: 5636223 (Open Web Text)

Max Activating Token Index: 559