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

Dataset: Open Web Text

Neuron 872 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: 3.1729. Min Range: -3.1729

Max Act: 3.1660. Min Act: -0.1700

Data Index: 3011217 (Open Web Text)

Max Activating Token Index: 585

Text #1

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.1729. Min Act: -0.1700

Data Index: 8765645 (Open Web Text)

Max Activating Token Index: 632

Text #2

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.1727. Min Act: -0.1700

Data Index: 2168411 (Open Web Text)

Max Activating Token Index: 668

Text #3

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.1495. Min Act: -0.1700

Data Index: 6232976 (Open Web Text)

Max Activating Token Index: 989

Text #4

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.1323. Min Act: -0.1700

Data Index: 5791178 (Open Web Text)

Max Activating Token Index: 820

Text #5

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.1314. Min Act: -0.1700

Data Index: 5064153 (Open Web Text)

Max Activating Token Index: 1007

Text #6

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.1159. Min Act: -0.1700

Data Index: 3357941 (Open Web Text)

Max Activating Token Index: 206

Text #7

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0965. Min Act: -0.1700

Data Index: 6661531 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0783. Min Act: -0.1700

Data Index: 3082411 (Open Web Text)

Max Activating Token Index: 880

Text #9

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0871. Min Act: -0.1700

Data Index: 4517801 (Open Web Text)

Max Activating Token Index: 348

Text #10

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0836. Min Act: -0.1700

Data Index: 443197 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0749. Min Act: -0.1700

Data Index: 4551693 (Open Web Text)

Max Activating Token Index: 864

Text #12

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0572. Min Act: -0.1700

Data Index: 4035694 (Open Web Text)

Max Activating Token Index: 388

Text #13

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0728. Min Act: -0.1700

Data Index: 8146306 (Open Web Text)

Max Activating Token Index: 268

Text #14

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0437. Min Act: -0.1700

Data Index: 4098384 (Open Web Text)

Max Activating Token Index: 828

Text #15

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0379. Min Act: -0.1700

Data Index: 2395606 (Open Web Text)

Max Activating Token Index: 898

Text #16

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0556. Min Act: -0.1700

Data Index: 3675214 (Open Web Text)

Max Activating Token Index: 772

Text #17

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0421. Min Act: -0.1700

Data Index: 628107 (Open Web Text)

Max Activating Token Index: 569

Text #18

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0261. Min Act: -0.1700

Data Index: 3162496 (Open Web Text)

Max Activating Token Index: 449

Text #19

Max Range: 3.1729. Min Range: -3.1729

Max Act: 3.0398. Min Act: -0.1700

Data Index: 644684 (Open Web Text)

Max Activating Token Index: 346