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

Dataset: Open Web Text

Neuron 307 in Layer 3

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: 4.8642. Min Range: -4.8642

Max Act: 4.8642. Min Act: -0.1700

Data Index: 7058801 (Open Web Text)

Max Activating Token Index: 624

Text #1

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.7769. Min Act: -0.1700

Data Index: 2591800 (Open Web Text)

Max Activating Token Index: 942

Text #2

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.7068. Min Act: -0.1700

Data Index: 3985132 (Open Web Text)

Max Activating Token Index: 585

Text #3

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.7832. Min Act: -0.1700

Data Index: 3216926 (Open Web Text)

Max Activating Token Index: 690

Text #4

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.7055. Min Act: -0.1700

Data Index: 6922966 (Open Web Text)

Max Activating Token Index: 98

Text #5

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6616. Min Act: -0.1700

Data Index: 8233975 (Open Web Text)

Max Activating Token Index: 264

Text #6

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6656. Min Act: -0.1700

Data Index: 118377 (Open Web Text)

Max Activating Token Index: 976

Text #7

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6529. Min Act: -0.1700

Data Index: 3581438 (Open Web Text)

Max Activating Token Index: 623

Text #8

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6051. Min Act: -0.1700

Data Index: 5392789 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6073. Min Act: -0.1700

Data Index: 4376119 (Open Web Text)

Max Activating Token Index: 554

Text #10

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6721. Min Act: -0.1700

Data Index: 749521 (Open Web Text)

Max Activating Token Index: 954

Text #11

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6431. Min Act: -0.1700

Data Index: 8016796 (Open Web Text)

Max Activating Token Index: 613

Text #12

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6629. Min Act: -0.1700

Data Index: 7762624 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6773. Min Act: -0.1700

Data Index: 2035102 (Open Web Text)

Max Activating Token Index: 933

Text #14

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6344. Min Act: -0.1700

Data Index: 6653682 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.5990. Min Act: -0.1700

Data Index: 5930408 (Open Web Text)

Max Activating Token Index: 436

Text #16

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6273. Min Act: -0.1700

Data Index: 7753570 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6903. Min Act: -0.1700

Data Index: 3361093 (Open Web Text)

Max Activating Token Index: 590

Text #18

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.6094. Min Act: -0.1700

Data Index: 7224713 (Open Web Text)

Max Activating Token Index: 77

Text #19

Max Range: 4.8642. Min Range: -4.8642

Max Act: 4.5396. Min Act: -0.1700

Data Index: 7347709 (Open Web Text)

Max Activating Token Index: 205