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

Dataset: Open Web Text

Neuron 2298 in Layer 6

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: 4.4624. Min Range: -4.4624

Max Act: 4.4624. Min Act: -0.1700

Data Index: 2835959 (Open Web Text)

Max Activating Token Index: 430

Text #1

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2811. Min Act: -0.1700

Data Index: 512584 (Open Web Text)

Max Activating Token Index: 724

Text #2

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2606. Min Act: -0.1700

Data Index: 5899957 (Open Web Text)

Max Activating Token Index: 424

Text #3

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2418. Min Act: -0.1700

Data Index: 2832694 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2634. Min Act: -0.1700

Data Index: 6539523 (Open Web Text)

Max Activating Token Index: 302

Text #5

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2582. Min Act: -0.1700

Data Index: 5834658 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2730. Min Act: -0.1700

Data Index: 7347369 (Open Web Text)

Max Activating Token Index: 298

Text #7

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2251. Min Act: -0.1700

Data Index: 2524253 (Open Web Text)

Max Activating Token Index: 325

Text #8

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2009. Min Act: -0.1700

Data Index: 8058292 (Open Web Text)

Max Activating Token Index: 445

Text #9

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2414. Min Act: -0.1700

Data Index: 1528291 (Open Web Text)

Max Activating Token Index: 440

Text #10

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2003. Min Act: -0.1700

Data Index: 4626227 (Open Web Text)

Max Activating Token Index: 217

Text #11

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2096. Min Act: -0.1700

Data Index: 3716387 (Open Web Text)

Max Activating Token Index: 247

Text #12

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1867. Min Act: -0.1700

Data Index: 1033160 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1655. Min Act: -0.1700

Data Index: 5060828 (Open Web Text)

Max Activating Token Index: 760

Text #14

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1810. Min Act: -0.1700

Data Index: 3644731 (Open Web Text)

Max Activating Token Index: 853

Text #15

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1746. Min Act: -0.1700

Data Index: 4625322 (Open Web Text)

Max Activating Token Index: 180

Text #16

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1847. Min Act: -0.1700

Data Index: 2475044 (Open Web Text)

Max Activating Token Index: 283

Text #17

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1855. Min Act: -0.1700

Data Index: 2676437 (Open Web Text)

Max Activating Token Index: 874

Text #18

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1412. Min Act: -0.1700

Data Index: 4621016 (Open Web Text)

Max Activating Token Index: 752

Text #19

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1508. Min Act: -0.1700

Data Index: 4864148 (Open Web Text)

Max Activating Token Index: 654