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

Dataset: Open Web Text

Neuron 481 in Layer 1

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: 3.1486. Min Range: -3.1486

Max Act: 3.1486. Min Act: -0.1700

Data Index: 5699838 (Open Web Text)

Max Activating Token Index: 256

Text #1

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.9027. Min Act: -0.1700

Data Index: 4871354 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.3576. Min Act: -0.1700

Data Index: 3096606 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.3215. Min Act: -0.1700

Data Index: 5451436 (Open Web Text)

Max Activating Token Index: 330

Text #4

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.3042. Min Act: -0.1700

Data Index: 20651 (Open Web Text)

Max Activating Token Index: 627

Text #5

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2871. Min Act: -0.1700

Data Index: 4281471 (Open Web Text)

Max Activating Token Index: 707

Text #6

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2980. Min Act: -0.1700

Data Index: 1774033 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2658. Min Act: -0.1700

Data Index: 219450 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2546. Min Act: -0.1700

Data Index: 192082 (Open Web Text)

Max Activating Token Index: 299

Text #9

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2617. Min Act: -0.1698

Data Index: 1774042 (Open Web Text)

Max Activating Token Index: 931

Text #10

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2545. Min Act: -0.1700

Data Index: 4899492 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2489. Min Act: -0.1700

Data Index: 4570034 (Open Web Text)

Max Activating Token Index: 509

Text #12

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2317. Min Act: -0.1700

Data Index: 4915553 (Open Web Text)

Max Activating Token Index: 926

Text #13

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2254. Min Act: -0.1700

Data Index: 4432712 (Open Web Text)

Max Activating Token Index: 604

Text #14

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2348. Min Act: -0.1700

Data Index: 863139 (Open Web Text)

Max Activating Token Index: 728

Text #15

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2155. Min Act: -0.1700

Data Index: 7528430 (Open Web Text)

Max Activating Token Index: 859

Text #16

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.2082. Min Act: -0.1700

Data Index: 3782538 (Open Web Text)

Max Activating Token Index: 177

Text #17

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.1753. Min Act: -0.1700

Data Index: 7953979 (Open Web Text)

Max Activating Token Index: 192

Text #18

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.1883. Min Act: -0.1700

Data Index: 8770643 (Open Web Text)

Max Activating Token Index: 698

Text #19

Max Range: 3.1486. Min Range: -3.1486

Max Act: 2.1813. Min Act: -0.1700

Data Index: 5527408 (Open Web Text)

Max Activating Token Index: 612