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

Dataset: Open Web Text

Neuron 266 in Layer 5

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: 4.9714. Min Range: -4.9714

Max Act: 4.9714. Min Act: -0.1700

Data Index: 1061420 (Open Web Text)

Max Activating Token Index: 1013

Text #1

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.8364. Min Act: -0.1700

Data Index: 758591 (Open Web Text)

Max Activating Token Index: 231

Text #2

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.7924. Min Act: -0.1700

Data Index: 7030511 (Open Web Text)

Max Activating Token Index: 944

Text #3

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.8053. Min Act: -0.1700

Data Index: 7532633 (Open Web Text)

Max Activating Token Index: 753

Text #4

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.7805. Min Act: -0.1700

Data Index: 4131659 (Open Web Text)

Max Activating Token Index: 796

Text #5

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.7388. Min Act: -0.1700

Data Index: 5537841 (Open Web Text)

Max Activating Token Index: 242

Text #6

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.6970. Min Act: -0.1700

Data Index: 6238561 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.7477. Min Act: -0.1700

Data Index: 118903 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.7320. Min Act: -0.1700

Data Index: 3321891 (Open Web Text)

Max Activating Token Index: 1012

Text #9

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.7243. Min Act: -0.1700

Data Index: 3697109 (Open Web Text)

Max Activating Token Index: 885

Text #10

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.7293. Min Act: -0.1700

Data Index: 5342779 (Open Web Text)

Max Activating Token Index: 305

Text #11

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.6825. Min Act: -0.1700

Data Index: 5928767 (Open Web Text)

Max Activating Token Index: 158

Text #12

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.6727. Min Act: -0.1700

Data Index: 2120660 (Open Web Text)

Max Activating Token Index: 548

Text #13

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.7121. Min Act: -0.1700

Data Index: 531716 (Open Web Text)

Max Activating Token Index: 624

Text #14

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.6753. Min Act: -0.1700

Data Index: 6770043 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.6780. Min Act: -0.1700

Data Index: 730769 (Open Web Text)

Max Activating Token Index: 536

Text #16

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.6799. Min Act: -0.1700

Data Index: 4158552 (Open Web Text)

Max Activating Token Index: 195

Text #17

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.6808. Min Act: -0.1700

Data Index: 3310057 (Open Web Text)

Max Activating Token Index: 70

Text #18

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.6945. Min Act: -0.1700

Data Index: 5530051 (Open Web Text)

Max Activating Token Index: 995

Text #19

Max Range: 4.9714. Min Range: -4.9714

Max Act: 4.7265. Min Act: -0.1700

Data Index: 2546355 (Open Web Text)

Max Activating Token Index: 669