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

Dataset: Open Web Text

Neuron 887 in Layer 2

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: 3.9540. Min Range: -3.9540

Max Act: 3.9540. Min Act: -0.1700

Data Index: 7138570 (Open Web Text)

Max Activating Token Index: 952

Text #1

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.8469. Min Act: -0.1700

Data Index: 6295733 (Open Web Text)

Max Activating Token Index: 850

Text #2

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.8057. Min Act: -0.1700

Data Index: 854032 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7530. Min Act: -0.1700

Data Index: 5339274 (Open Web Text)

Max Activating Token Index: 584

Text #4

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7538. Min Act: -0.1700

Data Index: 6985250 (Open Web Text)

Max Activating Token Index: 328

Text #5

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7628. Min Act: -0.1700

Data Index: 1983644 (Open Web Text)

Max Activating Token Index: 434

Text #6

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7566. Min Act: -0.1700

Data Index: 4799632 (Open Web Text)

Max Activating Token Index: 496

Text #7

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7411. Min Act: -0.1700

Data Index: 3722399 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7311. Min Act: -0.1700

Data Index: 1408048 (Open Web Text)

Max Activating Token Index: 264

Text #9

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7118. Min Act: -0.1700

Data Index: 2971826 (Open Web Text)

Max Activating Token Index: 105

Text #10

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.6674. Min Act: -0.1700

Data Index: 730107 (Open Web Text)

Max Activating Token Index: 307

Text #11

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7086. Min Act: -0.1700

Data Index: 3498617 (Open Web Text)

Max Activating Token Index: 402

Text #12

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7093. Min Act: -0.1700

Data Index: 2272661 (Open Web Text)

Max Activating Token Index: 208

Text #13

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7075. Min Act: -0.1700

Data Index: 1481279 (Open Web Text)

Max Activating Token Index: 942

Text #14

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.6988. Min Act: -0.1700

Data Index: 5018028 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.6564. Min Act: -0.1700

Data Index: 5923546 (Open Web Text)

Max Activating Token Index: 195

Text #16

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.7115. Min Act: -0.1700

Data Index: 4268869 (Open Web Text)

Max Activating Token Index: 593

Text #17

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.6459. Min Act: -0.1700

Data Index: 4627808 (Open Web Text)

Max Activating Token Index: 741

Text #18

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.6559. Min Act: -0.1700

Data Index: 951541 (Open Web Text)

Max Activating Token Index: 625

Text #19

Max Range: 3.9540. Min Range: -3.9540

Max Act: 3.6347. Min Act: -0.1700

Data Index: 3701309 (Open Web Text)

Max Activating Token Index: 174