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

Dataset: Open Web Text

Neuron 651 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: 3.6961. Min Range: -3.6961

Max Act: 3.6961. Min Act: -0.1700

Data Index: 7693869 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.6581. Min Act: -0.1700

Data Index: 7254320 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.6195. Min Act: -0.1700

Data Index: 4181021 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.6511. Min Act: -0.1700

Data Index: 3197145 (Open Web Text)

Max Activating Token Index: 350

Text #4

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.6527. Min Act: -0.1700

Data Index: 8074767 (Open Web Text)

Max Activating Token Index: 865

Text #5

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5796. Min Act: -0.1700

Data Index: 3875557 (Open Web Text)

Max Activating Token Index: 316

Text #6

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5555. Min Act: -0.1700

Data Index: 1902463 (Open Web Text)

Max Activating Token Index: 690

Text #7

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5918. Min Act: -0.1700

Data Index: 645134 (Open Web Text)

Max Activating Token Index: 1010

Text #8

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5795. Min Act: -0.1700

Data Index: 2572393 (Open Web Text)

Max Activating Token Index: 128

Text #9

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5702. Min Act: -0.1700

Data Index: 5770842 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5393. Min Act: -0.1700

Data Index: 2744425 (Open Web Text)

Max Activating Token Index: 250

Text #11

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5587. Min Act: -0.1700

Data Index: 3778331 (Open Web Text)

Max Activating Token Index: 70

Text #12

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5527. Min Act: -0.1700

Data Index: 3845806 (Open Web Text)

Max Activating Token Index: 235

Text #13

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5364. Min Act: -0.1700

Data Index: 8209605 (Open Web Text)

Max Activating Token Index: 25

Text #14

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5414. Min Act: -0.1700

Data Index: 889555 (Open Web Text)

Max Activating Token Index: 216

Text #15

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5290. Min Act: -0.1700

Data Index: 7800090 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5188. Min Act: -0.1700

Data Index: 8023399 (Open Web Text)

Max Activating Token Index: 150

Text #17

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5608. Min Act: -0.1700

Data Index: 3603503 (Open Web Text)

Max Activating Token Index: 804

Text #18

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5326. Min Act: -0.1700

Data Index: 4416085 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 3.6961. Min Range: -3.6961

Max Act: 3.5375. Min Act: -0.1700

Data Index: 6056556 (Open Web Text)

Max Activating Token Index: 773