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

Dataset: Open Web Text

Neuron 2127 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: 4.3188. Min Range: -4.3188

Max Act: 4.3188. Min Act: -0.1700

Data Index: 3953580 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.3056. Min Act: -0.1700

Data Index: 4290150 (Open Web Text)

Max Activating Token Index: 665

Text #2

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.2674. Min Act: -0.1700

Data Index: 8014074 (Open Web Text)

Max Activating Token Index: 163

Text #3

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.2575. Min Act: -0.1700

Data Index: 812602 (Open Web Text)

Max Activating Token Index: 282

Text #4

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.2316. Min Act: -0.1700

Data Index: 3930117 (Open Web Text)

Max Activating Token Index: 646

Text #5

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.2556. Min Act: -0.1700

Data Index: 4192685 (Open Web Text)

Max Activating Token Index: 811

Text #6

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.2125. Min Act: -0.1700

Data Index: 649692 (Open Web Text)

Max Activating Token Index: 665

Text #7

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.1497. Min Act: -0.1700

Data Index: 8826627 (Open Web Text)

Max Activating Token Index: 172

Text #8

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.1756. Min Act: -0.1700

Data Index: 4332268 (Open Web Text)

Max Activating Token Index: 150

Text #9

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.1949. Min Act: -0.1700

Data Index: 6433607 (Open Web Text)

Max Activating Token Index: 779

Text #10

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.1221. Min Act: -0.1700

Data Index: 3036690 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.1544. Min Act: -0.1700

Data Index: 6981009 (Open Web Text)

Max Activating Token Index: 637

Text #12

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.1256. Min Act: -0.1700

Data Index: 7881467 (Open Web Text)

Max Activating Token Index: 742

Text #13

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.1439. Min Act: -0.1700

Data Index: 3404003 (Open Web Text)

Max Activating Token Index: 879

Text #14

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.1229. Min Act: -0.1700

Data Index: 6526993 (Open Web Text)

Max Activating Token Index: 538

Text #15

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.1068. Min Act: -0.1700

Data Index: 4968427 (Open Web Text)

Max Activating Token Index: 928

Text #16

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.0946. Min Act: -0.1700

Data Index: 7624740 (Open Web Text)

Max Activating Token Index: 228

Text #17

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.1194. Min Act: -0.1700

Data Index: 6108025 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.0838. Min Act: -0.1700

Data Index: 5887827 (Open Web Text)

Max Activating Token Index: 394

Text #19

Max Range: 4.3188. Min Range: -4.3188

Max Act: 4.0835. Min Act: -0.1700

Data Index: 3163787 (Open Web Text)

Max Activating Token Index: 662