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

Dataset: Open Web Text

Neuron 498 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: 1.5820. Min Range: -1.5820

Max Act: 1.5820. Min Act: -0.1700

Data Index: 3428815 (Open Web Text)

Max Activating Token Index: 247

Text #1

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5481. Min Act: -0.1694

Data Index: 2672713 (Open Web Text)

Max Activating Token Index: 136

Text #2

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5275. Min Act: -0.1696

Data Index: 1807393 (Open Web Text)

Max Activating Token Index: 509

Text #3

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5142. Min Act: -0.1683

Data Index: 2378627 (Open Web Text)

Max Activating Token Index: 687

Text #4

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4998. Min Act: -0.1699

Data Index: 118478 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4955. Min Act: -0.1700

Data Index: 2785188 (Open Web Text)

Max Activating Token Index: 952

Text #6

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4897. Min Act: -0.1700

Data Index: 73619 (Open Web Text)

Max Activating Token Index: 308

Text #7

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4957. Min Act: -0.1700

Data Index: 3482398 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4886. Min Act: -0.1700

Data Index: 2378630 (Open Web Text)

Max Activating Token Index: 968

Text #9

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4814. Min Act: -0.1698

Data Index: 2010391 (Open Web Text)

Max Activating Token Index: 192

Text #10

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4807. Min Act: -0.1641

Data Index: 2252695 (Open Web Text)

Max Activating Token Index: 929

Text #11

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4755. Min Act: -0.1697

Data Index: 2920602 (Open Web Text)

Max Activating Token Index: 974

Text #12

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4675. Min Act: -0.1700

Data Index: 517376 (Open Web Text)

Max Activating Token Index: 904

Text #13

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4804. Min Act: -0.1700

Data Index: 2106652 (Open Web Text)

Max Activating Token Index: 126

Text #14

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4837. Min Act: -0.1685

Data Index: 8617678 (Open Web Text)

Max Activating Token Index: 498

Text #15

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4713. Min Act: -0.1700

Data Index: 8535154 (Open Web Text)

Max Activating Token Index: 62

Text #16

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4808. Min Act: -0.1697

Data Index: 2730153 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4657. Min Act: -0.1682

Data Index: 1287398 (Open Web Text)

Max Activating Token Index: 178

Text #18

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4588. Min Act: -0.1692

Data Index: 7322453 (Open Web Text)

Max Activating Token Index: 380

Text #19

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.4572. Min Act: -0.1700

Data Index: 6256498 (Open Web Text)

Max Activating Token Index: 892