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

Dataset: Open Web Text

Neuron 218 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: 4.2076. Min Range: -4.2076

Max Act: 4.2076. Min Act: -0.1700

Data Index: 944651 (Open Web Text)

Max Activating Token Index: 681

Text #1

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.1774. Min Act: -0.1700

Data Index: 5992633 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.1715. Min Act: -0.1700

Data Index: 6367236 (Open Web Text)

Max Activating Token Index: 307

Text #3

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.1634. Min Act: -0.1700

Data Index: 3336633 (Open Web Text)

Max Activating Token Index: 484

Text #4

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.1479. Min Act: -0.1700

Data Index: 1742536 (Open Web Text)

Max Activating Token Index: 245

Text #5

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.1096. Min Act: -0.1700

Data Index: 2798214 (Open Web Text)

Max Activating Token Index: 75

Text #6

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.1179. Min Act: -0.1700

Data Index: 5213022 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0773. Min Act: -0.1700

Data Index: 176680 (Open Web Text)

Max Activating Token Index: 474

Text #8

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0991. Min Act: -0.1700

Data Index: 764548 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0819. Min Act: -0.1700

Data Index: 2538986 (Open Web Text)

Max Activating Token Index: 726

Text #10

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0874. Min Act: -0.1700

Data Index: 6752167 (Open Web Text)

Max Activating Token Index: 538

Text #11

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.1058. Min Act: -0.1700

Data Index: 6411351 (Open Web Text)

Max Activating Token Index: 40

Text #12

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0817. Min Act: -0.1700

Data Index: 1695488 (Open Web Text)

Max Activating Token Index: 568

Text #13

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0657. Min Act: -0.1700

Data Index: 4596785 (Open Web Text)

Max Activating Token Index: 122

Text #14

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0710. Min Act: -0.1700

Data Index: 1608792 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0551. Min Act: -0.1700

Data Index: 4510726 (Open Web Text)

Max Activating Token Index: 572

Text #16

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0922. Min Act: -0.1700

Data Index: 2068363 (Open Web Text)

Max Activating Token Index: 933

Text #17

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0646. Min Act: -0.1700

Data Index: 2248557 (Open Web Text)

Max Activating Token Index: 84

Text #18

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0413. Min Act: -0.1700

Data Index: 5510819 (Open Web Text)

Max Activating Token Index: 1017

Text #19

Max Range: 4.2076. Min Range: -4.2076

Max Act: 4.0700. Min Act: -0.1700

Data Index: 6015774 (Open Web Text)

Max Activating Token Index: 8