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

Dataset: Open Web Text

Neuron 34 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: 1.7772. Min Range: -1.7772

Max Act: 1.7772. Min Act: -0.1700

Data Index: 3546050 (Open Web Text)

Max Activating Token Index: 24

Text #1

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.7591. Min Act: -0.1700

Data Index: 3758256 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.7207. Min Act: -0.1700

Data Index: 3781785 (Open Web Text)

Max Activating Token Index: 361

Text #3

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.7098. Min Act: -0.1700

Data Index: 8716739 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.7023. Min Act: -0.1700

Data Index: 4861341 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.7021. Min Act: -0.1700

Data Index: 8251103 (Open Web Text)

Max Activating Token Index: 269

Text #6

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6994. Min Act: -0.1700

Data Index: 2775812 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6902. Min Act: -0.1700

Data Index: 2284328 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6968. Min Act: -0.1700

Data Index: 4868700 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6814. Min Act: -0.1699

Data Index: 855516 (Open Web Text)

Max Activating Token Index: 148

Text #10

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6758. Min Act: -0.1700

Data Index: 4156092 (Open Web Text)

Max Activating Token Index: 453

Text #11

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6543. Min Act: -0.1700

Data Index: 2922724 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6693. Min Act: -0.1700

Data Index: 3746460 (Open Web Text)

Max Activating Token Index: 170

Text #13

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6648. Min Act: -0.1700

Data Index: 5189342 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6514. Min Act: -0.1700

Data Index: 8391927 (Open Web Text)

Max Activating Token Index: 307

Text #15

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6538. Min Act: -0.1700

Data Index: 7076825 (Open Web Text)

Max Activating Token Index: 185

Text #16

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6635. Min Act: -0.1700

Data Index: 5374297 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6603. Min Act: -0.1700

Data Index: 5769972 (Open Web Text)

Max Activating Token Index: 77

Text #18

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6418. Min Act: -0.1700

Data Index: 3855356 (Open Web Text)

Max Activating Token Index: 122

Text #19

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.6352. Min Act: -0.1700

Data Index: 630491 (Open Web Text)

Max Activating Token Index: 39