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

Dataset: Open Web Text

Neuron 680 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: 4.2966. Min Range: -4.2966

Max Act: 4.2966. Min Act: -0.1700

Data Index: 3675377 (Open Web Text)

Max Activating Token Index: 720

Text #1

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.2739. Min Act: -0.1700

Data Index: 1519787 (Open Web Text)

Max Activating Token Index: 415

Text #2

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1902. Min Act: -0.1700

Data Index: 5947592 (Open Web Text)

Max Activating Token Index: 82

Text #3

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1895. Min Act: -0.1700

Data Index: 6670117 (Open Web Text)

Max Activating Token Index: 482

Text #4

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1632. Min Act: -0.1700

Data Index: 4944794 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1687. Min Act: -0.1700

Data Index: 4354365 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1681. Min Act: -0.1700

Data Index: 2765220 (Open Web Text)

Max Activating Token Index: 157

Text #7

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1588. Min Act: -0.1700

Data Index: 31933 (Open Web Text)

Max Activating Token Index: 182

Text #8

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1890. Min Act: -0.1700

Data Index: 1579309 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1667. Min Act: -0.1700

Data Index: 1539413 (Open Web Text)

Max Activating Token Index: 825

Text #10

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1814. Min Act: -0.1700

Data Index: 8408268 (Open Web Text)

Max Activating Token Index: 66

Text #11

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1402. Min Act: -0.1700

Data Index: 2037057 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1571. Min Act: -0.1700

Data Index: 3236149 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1329. Min Act: -0.1700

Data Index: 1547652 (Open Web Text)

Max Activating Token Index: 455

Text #14

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1615. Min Act: -0.1700

Data Index: 4393459 (Open Web Text)

Max Activating Token Index: 102

Text #15

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1489. Min Act: -0.1700

Data Index: 4741636 (Open Web Text)

Max Activating Token Index: 120

Text #16

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1460. Min Act: -0.1700

Data Index: 5584110 (Open Web Text)

Max Activating Token Index: 454

Text #17

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1270. Min Act: -0.1700

Data Index: 6156170 (Open Web Text)

Max Activating Token Index: 447

Text #18

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1541. Min Act: -0.1700

Data Index: 318831 (Open Web Text)

Max Activating Token Index: 909

Text #19

Max Range: 4.2966. Min Range: -4.2966

Max Act: 4.1648. Min Act: -0.1700

Data Index: 6559272 (Open Web Text)

Max Activating Token Index: 470