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

Dataset: Open Web Text

Neuron 323 in Layer 4

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: 4.0019. Min Range: -4.0019

Max Act: 4.0019. Min Act: -0.1700

Data Index: 4882986 (Open Web Text)

Max Activating Token Index: 641

Text #1

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.9425. Min Act: -0.1700

Data Index: 1017047 (Open Web Text)

Max Activating Token Index: 654

Text #2

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.8844. Min Act: -0.1700

Data Index: 2959501 (Open Web Text)

Max Activating Token Index: 535

Text #3

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.8583. Min Act: -0.1700

Data Index: 5169909 (Open Web Text)

Max Activating Token Index: 807

Text #4

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.8218. Min Act: -0.1700

Data Index: 7220344 (Open Web Text)

Max Activating Token Index: 771

Text #5

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.8495. Min Act: -0.1700

Data Index: 5087550 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.8251. Min Act: -0.1700

Data Index: 6987100 (Open Web Text)

Max Activating Token Index: 110

Text #7

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.8138. Min Act: -0.1700

Data Index: 7878045 (Open Web Text)

Max Activating Token Index: 847

Text #8

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7702. Min Act: -0.1700

Data Index: 2537028 (Open Web Text)

Max Activating Token Index: 722

Text #9

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7937. Min Act: -0.1700

Data Index: 2920732 (Open Web Text)

Max Activating Token Index: 96

Text #10

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7710. Min Act: -0.1700

Data Index: 7812025 (Open Web Text)

Max Activating Token Index: 668

Text #11

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7810. Min Act: -0.1700

Data Index: 7108570 (Open Web Text)

Max Activating Token Index: 715

Text #12

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.8085. Min Act: -0.1700

Data Index: 5420140 (Open Web Text)

Max Activating Token Index: 114

Text #13

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7934. Min Act: -0.1700

Data Index: 5942636 (Open Web Text)

Max Activating Token Index: 516

Text #14

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7991. Min Act: -0.1700

Data Index: 8338290 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7676. Min Act: -0.1700

Data Index: 5925718 (Open Web Text)

Max Activating Token Index: 68

Text #16

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7681. Min Act: -0.1700

Data Index: 8567604 (Open Web Text)

Max Activating Token Index: 254

Text #17

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7546. Min Act: -0.1700

Data Index: 7370984 (Open Web Text)

Max Activating Token Index: 523

Text #18

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7495. Min Act: -0.1700

Data Index: 1485041 (Open Web Text)

Max Activating Token Index: 578

Text #19

Max Range: 4.0019. Min Range: -4.0019

Max Act: 3.7374. Min Act: -0.1700

Data Index: 1535276 (Open Web Text)

Max Activating Token Index: 524