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

Dataset: Open Web Text

Neuron 2128 in Layer 4

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: 3.8746. Min Range: -3.8746

Max Act: 3.8514. Min Act: -0.1700

Data Index: 4115165 (Open Web Text)

Max Activating Token Index: 1005

Text #1

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.8746. Min Act: -0.1700

Data Index: 4781635 (Open Web Text)

Max Activating Token Index: 531

Text #2

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.7236. Min Act: -0.1700

Data Index: 4231847 (Open Web Text)

Max Activating Token Index: 361

Text #3

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.6633. Min Act: -0.1700

Data Index: 5132073 (Open Web Text)

Max Activating Token Index: 593

Text #4

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.6756. Min Act: -0.1700

Data Index: 7004578 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.6372. Min Act: -0.1700

Data Index: 207478 (Open Web Text)

Max Activating Token Index: 318

Text #6

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.5949. Min Act: -0.1700

Data Index: 2715334 (Open Web Text)

Max Activating Token Index: 73

Text #7

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.5534. Min Act: -0.1700

Data Index: 343578 (Open Web Text)

Max Activating Token Index: 182

Text #8

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.5627. Min Act: -0.1700

Data Index: 927266 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.5340. Min Act: -0.1700

Data Index: 207479 (Open Web Text)

Max Activating Token Index: 745

Text #10

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.5496. Min Act: -0.1700

Data Index: 6279161 (Open Web Text)

Max Activating Token Index: 760

Text #11

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.5196. Min Act: -0.1700

Data Index: 6713320 (Open Web Text)

Max Activating Token Index: 669

Text #12

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.5147. Min Act: -0.1700

Data Index: 7732558 (Open Web Text)

Max Activating Token Index: 878

Text #13

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.5042. Min Act: -0.1700

Data Index: 5525967 (Open Web Text)

Max Activating Token Index: 196

Text #14

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.5227. Min Act: -0.1700

Data Index: 6407115 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.5029. Min Act: -0.1700

Data Index: 5525969 (Open Web Text)

Max Activating Token Index: 213

Text #16

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.4951. Min Act: -0.1700

Data Index: 3489800 (Open Web Text)

Max Activating Token Index: 350

Text #17

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.4918. Min Act: -0.1700

Data Index: 3689060 (Open Web Text)

Max Activating Token Index: 957

Text #18

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.4770. Min Act: -0.1700

Data Index: 6457913 (Open Web Text)

Max Activating Token Index: 996

Text #19

Max Range: 3.8746. Min Range: -3.8746

Max Act: 3.4739. Min Act: -0.1700

Data Index: 5525968 (Open Web Text)

Max Activating Token Index: 9