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

Dataset: Open Web Text

Neuron 299 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: 4.1063. Min Range: -4.1063

Max Act: 4.1063. Min Act: -0.1700

Data Index: 5631733 (Open Web Text)

Max Activating Token Index: 642

Text #1

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.9748. Min Act: -0.1700

Data Index: 3132742 (Open Web Text)

Max Activating Token Index: 585

Text #2

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.9684. Min Act: -0.1700

Data Index: 7442136 (Open Web Text)

Max Activating Token Index: 135

Text #3

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.9620. Min Act: -0.1700

Data Index: 4262984 (Open Web Text)

Max Activating Token Index: 689

Text #4

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.9464. Min Act: -0.1700

Data Index: 8092394 (Open Web Text)

Max Activating Token Index: 537

Text #5

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.9554. Min Act: -0.1700

Data Index: 5150165 (Open Web Text)

Max Activating Token Index: 759

Text #6

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8961. Min Act: -0.1700

Data Index: 2842650 (Open Web Text)

Max Activating Token Index: 611

Text #7

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8987. Min Act: -0.1700

Data Index: 5676379 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8993. Min Act: -0.1700

Data Index: 993080 (Open Web Text)

Max Activating Token Index: 598

Text #9

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8957. Min Act: -0.1700

Data Index: 4631006 (Open Web Text)

Max Activating Token Index: 126

Text #10

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.9180. Min Act: -0.1700

Data Index: 344388 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8853. Min Act: -0.1700

Data Index: 1400027 (Open Web Text)

Max Activating Token Index: 434

Text #12

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8789. Min Act: -0.1700

Data Index: 2630842 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8794. Min Act: -0.1700

Data Index: 6896048 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8600. Min Act: -0.1700

Data Index: 5190088 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8859. Min Act: -0.1700

Data Index: 2433445 (Open Web Text)

Max Activating Token Index: 790

Text #16

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8655. Min Act: -0.1700

Data Index: 5044386 (Open Web Text)

Max Activating Token Index: 732

Text #17

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8706. Min Act: -0.1700

Data Index: 6729685 (Open Web Text)

Max Activating Token Index: 381

Text #18

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8903. Min Act: -0.1700

Data Index: 6396071 (Open Web Text)

Max Activating Token Index: 560

Text #19

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.8738. Min Act: -0.1700

Data Index: 4572388 (Open Web Text)

Max Activating Token Index: 996