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

Dataset: Open Web Text

Neuron 474 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: 3.6909. Min Range: -3.6909

Max Act: 3.6633. Min Act: -0.1700

Data Index: 2157224 (Open Web Text)

Max Activating Token Index: 479

Text #1

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6729. Min Act: -0.1700

Data Index: 3813998 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6607. Min Act: -0.1700

Data Index: 3136221 (Open Web Text)

Max Activating Token Index: 275

Text #3

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6513. Min Act: -0.1700

Data Index: 8702324 (Open Web Text)

Max Activating Token Index: 692

Text #4

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6090. Min Act: -0.1700

Data Index: 2056865 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6510. Min Act: -0.1700

Data Index: 2060870 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6033. Min Act: -0.1700

Data Index: 979113 (Open Web Text)

Max Activating Token Index: 802

Text #7

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6314. Min Act: -0.1700

Data Index: 2552470 (Open Web Text)

Max Activating Token Index: 33

Text #8

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6349. Min Act: -0.1700

Data Index: 583485 (Open Web Text)

Max Activating Token Index: 425

Text #9

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6497. Min Act: -0.1699

Data Index: 3936608 (Open Web Text)

Max Activating Token Index: 422

Text #10

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6390. Min Act: -0.1700

Data Index: 813846 (Open Web Text)

Max Activating Token Index: 46

Text #11

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6435. Min Act: -0.1700

Data Index: 8587096 (Open Web Text)

Max Activating Token Index: 398

Text #12

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6077. Min Act: -0.1700

Data Index: 1601032 (Open Web Text)

Max Activating Token Index: 434

Text #13

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6909. Min Act: -0.1700

Data Index: 6767899 (Open Web Text)

Max Activating Token Index: 525

Text #14

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6289. Min Act: -0.1700

Data Index: 5719440 (Open Web Text)

Max Activating Token Index: 1007

Text #15

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5973. Min Act: -0.1699

Data Index: 4920528 (Open Web Text)

Max Activating Token Index: 846

Text #16

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6254. Min Act: -0.1698

Data Index: 284646 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5994. Min Act: -0.1700

Data Index: 868679 (Open Web Text)

Max Activating Token Index: 183

Text #18

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6058. Min Act: -0.1700

Data Index: 3560643 (Open Web Text)

Max Activating Token Index: 956

Text #19

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6157. Min Act: -0.1700

Data Index: 173518 (Open Web Text)

Max Activating Token Index: 432