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

Dataset: Open Web Text

Neuron 492 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: 1.4508. Min Range: -1.4508

Max Act: 1.4508. Min Act: -0.1687

Data Index: 6866891 (Open Web Text)

Max Activating Token Index: 274

Text #1

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4269. Min Act: -0.1699

Data Index: 433558 (Open Web Text)

Max Activating Token Index: 171

Text #2

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4256. Min Act: -0.1689

Data Index: 7385247 (Open Web Text)

Max Activating Token Index: 557

Text #3

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4311. Min Act: -0.1700

Data Index: 8003770 (Open Web Text)

Max Activating Token Index: 391

Text #4

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4319. Min Act: -0.1682

Data Index: 8699121 (Open Web Text)

Max Activating Token Index: 518

Text #5

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4198. Min Act: -0.1700

Data Index: 1499403 (Open Web Text)

Max Activating Token Index: 86

Text #6

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4033. Min Act: -0.1700

Data Index: 1080642 (Open Web Text)

Max Activating Token Index: 249

Text #7

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4046. Min Act: -0.1700

Data Index: 553189 (Open Web Text)

Max Activating Token Index: 141

Text #8

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3921. Min Act: -0.1700

Data Index: 5639656 (Open Web Text)

Max Activating Token Index: 396

Text #9

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3814. Min Act: -0.1621

Data Index: 3407727 (Open Web Text)

Max Activating Token Index: 630

Text #10

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3814. Min Act: -0.1700

Data Index: 4414512 (Open Web Text)

Max Activating Token Index: 483

Text #11

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3846. Min Act: -0.1700

Data Index: 7617179 (Open Web Text)

Max Activating Token Index: 47

Text #12

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3698. Min Act: -0.1700

Data Index: 7877222 (Open Web Text)

Max Activating Token Index: 921

Text #13

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3729. Min Act: -0.1698

Data Index: 7745085 (Open Web Text)

Max Activating Token Index: 218

Text #14

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3771. Min Act: -0.1700

Data Index: 7062626 (Open Web Text)

Max Activating Token Index: 404

Text #15

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3770. Min Act: -0.1699

Data Index: 1701914 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3719. Min Act: -0.1700

Data Index: 7955449 (Open Web Text)

Max Activating Token Index: 198

Text #17

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3704. Min Act: -0.1700

Data Index: 3597117 (Open Web Text)

Max Activating Token Index: 109

Text #18

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3624. Min Act: -0.1699

Data Index: 509370 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3653. Min Act: -0.1700

Data Index: 5681304 (Open Web Text)

Max Activating Token Index: 133