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

Dataset: Open Web Text

Neuron 2051 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: 1.5628. Min Range: -1.5628

Max Act: 1.5628. Min Act: -0.1645

Data Index: 1904310 (Open Web Text)

Max Activating Token Index: 656

Text #1

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5597. Min Act: -0.1700

Data Index: 133989 (Open Web Text)

Max Activating Token Index: 958

Text #2

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5455. Min Act: -0.1643

Data Index: 7457357 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5387. Min Act: -0.1487

Data Index: 5795444 (Open Web Text)

Max Activating Token Index: 220

Text #4

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5137. Min Act: -0.1694

Data Index: 1287471 (Open Web Text)

Max Activating Token Index: 921

Text #5

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5157. Min Act: -0.1695

Data Index: 5184551 (Open Web Text)

Max Activating Token Index: 268

Text #6

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5009. Min Act: -0.1684

Data Index: 2089327 (Open Web Text)

Max Activating Token Index: 739

Text #7

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5021. Min Act: -0.1655

Data Index: 6420464 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5103. Min Act: -0.1700

Data Index: 5083727 (Open Web Text)

Max Activating Token Index: 519

Text #9

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5062. Min Act: -0.1700

Data Index: 7992907 (Open Web Text)

Max Activating Token Index: 190

Text #10

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4992. Min Act: -0.1700

Data Index: 415661 (Open Web Text)

Max Activating Token Index: 157

Text #11

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4901. Min Act: -0.1591

Data Index: 2853825 (Open Web Text)

Max Activating Token Index: 458

Text #12

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4861. Min Act: -0.1697

Data Index: 2584671 (Open Web Text)

Max Activating Token Index: 867

Text #13

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4831. Min Act: -0.1679

Data Index: 8106495 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4894. Min Act: -0.1700

Data Index: 3109065 (Open Web Text)

Max Activating Token Index: 683

Text #15

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4729. Min Act: -0.1700

Data Index: 5749273 (Open Web Text)

Max Activating Token Index: 693

Text #16

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4791. Min Act: -0.1691

Data Index: 2591552 (Open Web Text)

Max Activating Token Index: 947

Text #17

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4762. Min Act: -0.1684

Data Index: 7010688 (Open Web Text)

Max Activating Token Index: 844

Text #18

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4867. Min Act: -0.1698

Data Index: 6615834 (Open Web Text)

Max Activating Token Index: 107

Text #19

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4758. Min Act: -0.1700

Data Index: 6870879 (Open Web Text)

Max Activating Token Index: 202