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

Dataset: Open Web Text

Neuron 2103 in Layer 5

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: 3.5074. Min Range: -3.5074

Max Act: 3.5074. Min Act: -0.1700

Data Index: 1142105 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.4299. Min Act: -0.1700

Data Index: 3820210 (Open Web Text)

Max Activating Token Index: 584

Text #2

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3746. Min Act: -0.1700

Data Index: 3744305 (Open Web Text)

Max Activating Token Index: 513

Text #3

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.2759. Min Act: -0.1700

Data Index: 5548926 (Open Web Text)

Max Activating Token Index: 528

Text #4

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.3365. Min Act: -0.1700

Data Index: 8269089 (Open Web Text)

Max Activating Token Index: 330

Text #5

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.2629. Min Act: -0.1700

Data Index: 1751529 (Open Web Text)

Max Activating Token Index: 496

Text #6

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.2749. Min Act: -0.1700

Data Index: 6294694 (Open Web Text)

Max Activating Token Index: 259

Text #7

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.2652. Min Act: -0.1700

Data Index: 757751 (Open Web Text)

Max Activating Token Index: 972

Text #8

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.2322. Min Act: -0.1700

Data Index: 2396693 (Open Web Text)

Max Activating Token Index: 482

Text #9

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.2058. Min Act: -0.1700

Data Index: 1258304 (Open Web Text)

Max Activating Token Index: 1020

Text #10

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.1518. Min Act: -0.1700

Data Index: 7637070 (Open Web Text)

Max Activating Token Index: 436

Text #11

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.0788. Min Act: -0.1700

Data Index: 6587785 (Open Web Text)

Max Activating Token Index: 1007

Text #12

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.1680. Min Act: -0.1700

Data Index: 143135 (Open Web Text)

Max Activating Token Index: 708

Text #13

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.2131. Min Act: -0.1700

Data Index: 8298752 (Open Web Text)

Max Activating Token Index: 469

Text #14

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.1618. Min Act: -0.1700

Data Index: 7249773 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.1811. Min Act: -0.1700

Data Index: 3492877 (Open Web Text)

Max Activating Token Index: 142

Text #16

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.1366. Min Act: -0.1700

Data Index: 2741640 (Open Web Text)

Max Activating Token Index: 767

Text #17

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.0933. Min Act: -0.1700

Data Index: 4064154 (Open Web Text)

Max Activating Token Index: 654

Text #18

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.0729. Min Act: -0.1700

Data Index: 7952716 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 3.5074. Min Range: -3.5074

Max Act: 3.0983. Min Act: -0.1700

Data Index: 81850 (Open Web Text)

Max Activating Token Index: 289