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

Dataset: Open Web Text

Neuron 786 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: 3.1726. Min Range: -3.1726

Max Act: 3.1726. Min Act: -0.1700

Data Index: 585459 (Open Web Text)

Max Activating Token Index: 781

Text #1

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.1496. Min Act: -0.1700

Data Index: 2183445 (Open Web Text)

Max Activating Token Index: 635

Text #2

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.1503. Min Act: -0.1700

Data Index: 3040644 (Open Web Text)

Max Activating Token Index: 634

Text #3

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.1326. Min Act: -0.1700

Data Index: 7710158 (Open Web Text)

Max Activating Token Index: 139

Text #4

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.1258. Min Act: -0.1700

Data Index: 2010589 (Open Web Text)

Max Activating Token Index: 603

Text #5

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.1229. Min Act: -0.1700

Data Index: 5421116 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0774. Min Act: -0.1700

Data Index: 7069898 (Open Web Text)

Max Activating Token Index: 324

Text #7

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0869. Min Act: -0.1700

Data Index: 7146123 (Open Web Text)

Max Activating Token Index: 264

Text #8

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0814. Min Act: -0.1700

Data Index: 4146758 (Open Web Text)

Max Activating Token Index: 773

Text #9

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0742. Min Act: -0.1700

Data Index: 1348201 (Open Web Text)

Max Activating Token Index: 961

Text #10

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0721. Min Act: -0.1700

Data Index: 3726660 (Open Web Text)

Max Activating Token Index: 947

Text #11

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0520. Min Act: -0.1700

Data Index: 3283511 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0558. Min Act: -0.1700

Data Index: 2696607 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0650. Min Act: -0.1700

Data Index: 5932769 (Open Web Text)

Max Activating Token Index: 557

Text #14

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0521. Min Act: -0.1700

Data Index: 1272015 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0579. Min Act: -0.1700

Data Index: 248169 (Open Web Text)

Max Activating Token Index: 172

Text #16

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0333. Min Act: -0.1700

Data Index: 4600204 (Open Web Text)

Max Activating Token Index: 803

Text #17

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0514. Min Act: -0.1700

Data Index: 3731312 (Open Web Text)

Max Activating Token Index: 607

Text #18

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0487. Min Act: -0.1700

Data Index: 9911 (Open Web Text)

Max Activating Token Index: 435

Text #19

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0405. Min Act: -0.1700

Data Index: 5182515 (Open Web Text)

Max Activating Token Index: 323