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

Dataset: Open Web Text

Neuron 790 in Layer 1

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: 4.5821. Min Range: -4.5821

Max Act: 4.5821. Min Act: -0.1700

Data Index: 1001429 (Open Web Text)

Max Activating Token Index: 130

Text #1

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.4887. Min Act: -0.1700

Data Index: 3562510 (Open Web Text)

Max Activating Token Index: 546

Text #2

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.3077. Min Act: -0.1700

Data Index: 5553914 (Open Web Text)

Max Activating Token Index: 129

Text #3

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.3117. Min Act: -0.1700

Data Index: 3293252 (Open Web Text)

Max Activating Token Index: 370

Text #4

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.2718. Min Act: -0.1700

Data Index: 5123092 (Open Web Text)

Max Activating Token Index: 568

Text #5

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.2185. Min Act: -0.1700

Data Index: 8307989 (Open Web Text)

Max Activating Token Index: 707

Text #6

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.2587. Min Act: -0.1700

Data Index: 2973791 (Open Web Text)

Max Activating Token Index: 111

Text #7

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.1851. Min Act: -0.1700

Data Index: 7879356 (Open Web Text)

Max Activating Token Index: 198

Text #8

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.1835. Min Act: -0.1700

Data Index: 649718 (Open Web Text)

Max Activating Token Index: 618

Text #9

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.1468. Min Act: -0.1700

Data Index: 1173753 (Open Web Text)

Max Activating Token Index: 143

Text #10

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.1586. Min Act: -0.1700

Data Index: 2840706 (Open Web Text)

Max Activating Token Index: 617

Text #11

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.1349. Min Act: -0.1700

Data Index: 5897789 (Open Web Text)

Max Activating Token Index: 467

Text #12

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.1095. Min Act: -0.1700

Data Index: 7470359 (Open Web Text)

Max Activating Token Index: 910

Text #13

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.0785. Min Act: -0.1700

Data Index: 6648884 (Open Web Text)

Max Activating Token Index: 644

Text #14

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.0579. Min Act: -0.1700

Data Index: 284426 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.0884. Min Act: -0.1700

Data Index: 8718758 (Open Web Text)

Max Activating Token Index: 570

Text #16

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.0385. Min Act: -0.1700

Data Index: 7088754 (Open Web Text)

Max Activating Token Index: 956

Text #17

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.0724. Min Act: -0.1700

Data Index: 3888495 (Open Web Text)

Max Activating Token Index: 419

Text #18

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.0771. Min Act: -0.1700

Data Index: 4811695 (Open Web Text)

Max Activating Token Index: 974

Text #19

Max Range: 4.5821. Min Range: -4.5821

Max Act: 4.0228. Min Act: -0.1700

Data Index: 2727934 (Open Web Text)

Max Activating Token Index: 285