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

Dataset: Open Web Text

Neuron 2659 in Layer 6

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: 4.8055. Min Range: -4.8055

Max Act: 4.8055. Min Act: -0.1700

Data Index: 7612444 (Open Web Text)

Max Activating Token Index: 983

Text #1

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.7508. Min Act: -0.1700

Data Index: 30391 (Open Web Text)

Max Activating Token Index: 549

Text #2

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.7043. Min Act: -0.1700

Data Index: 3811924 (Open Web Text)

Max Activating Token Index: 709

Text #3

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.7202. Min Act: -0.1700

Data Index: 5385816 (Open Web Text)

Max Activating Token Index: 545

Text #4

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.6594. Min Act: -0.1700

Data Index: 8656046 (Open Web Text)

Max Activating Token Index: 868

Text #5

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.6587. Min Act: -0.1700

Data Index: 8733741 (Open Web Text)

Max Activating Token Index: 864

Text #6

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.6457. Min Act: -0.1700

Data Index: 5191205 (Open Web Text)

Max Activating Token Index: 289

Text #7

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.6594. Min Act: -0.1700

Data Index: 6964047 (Open Web Text)

Max Activating Token Index: 454

Text #8

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.5927. Min Act: -0.1700

Data Index: 4570183 (Open Web Text)

Max Activating Token Index: 424

Text #9

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.5991. Min Act: -0.1700

Data Index: 4041145 (Open Web Text)

Max Activating Token Index: 294

Text #10

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.6105. Min Act: -0.1700

Data Index: 2541608 (Open Web Text)

Max Activating Token Index: 521

Text #11

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.5612. Min Act: -0.1700

Data Index: 7473955 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.5690. Min Act: -0.1700

Data Index: 3623368 (Open Web Text)

Max Activating Token Index: 949

Text #13

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.5827. Min Act: -0.1700

Data Index: 2386337 (Open Web Text)

Max Activating Token Index: 560

Text #14

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.5771. Min Act: -0.1700

Data Index: 2284114 (Open Web Text)

Max Activating Token Index: 961

Text #15

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.6231. Min Act: -0.1700

Data Index: 6270130 (Open Web Text)

Max Activating Token Index: 805

Text #16

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.5777. Min Act: -0.1700

Data Index: 5159936 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.5458. Min Act: -0.1700

Data Index: 3648302 (Open Web Text)

Max Activating Token Index: 465

Text #18

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.5532. Min Act: -0.1700

Data Index: 3685869 (Open Web Text)

Max Activating Token Index: 729

Text #19

Max Range: 4.8055. Min Range: -4.8055

Max Act: 4.5453. Min Act: -0.1700

Data Index: 830758 (Open Web Text)

Max Activating Token Index: 386