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

Dataset: Open Web Text

Neuron 3064 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: 5.3583. Min Range: -5.3583

Max Act: 5.3583. Min Act: -0.1700

Data Index: 3294941 (Open Web Text)

Max Activating Token Index: 287

Text #1

Max Range: 5.3583. Min Range: -5.3583

Max Act: 5.3299. Min Act: -0.1700

Data Index: 6045751 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 5.3583. Min Range: -5.3583

Max Act: 5.3466. Min Act: -0.1700

Data Index: 6205769 (Open Web Text)

Max Activating Token Index: 776

Text #3

Max Range: 5.3583. Min Range: -5.3583

Max Act: 5.0987. Min Act: -0.1700

Data Index: 2786219 (Open Web Text)

Max Activating Token Index: 964

Text #4

Max Range: 5.3583. Min Range: -5.3583

Max Act: 5.1242. Min Act: -0.1700

Data Index: 3435098 (Open Web Text)

Max Activating Token Index: 977

Text #5

Max Range: 5.3583. Min Range: -5.3583

Max Act: 5.0615. Min Act: -0.1700

Data Index: 5563237 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 5.3583. Min Range: -5.3583

Max Act: 5.0442. Min Act: -0.1700

Data Index: 3711780 (Open Web Text)

Max Activating Token Index: 603

Text #7

Max Range: 5.3583. Min Range: -5.3583

Max Act: 5.0326. Min Act: -0.1700

Data Index: 2592445 (Open Web Text)

Max Activating Token Index: 470

Text #8

Max Range: 5.3583. Min Range: -5.3583

Max Act: 5.0701. Min Act: -0.1700

Data Index: 3435090 (Open Web Text)

Max Activating Token Index: 158

Text #9

Max Range: 5.3583. Min Range: -5.3583

Max Act: 5.0051. Min Act: -0.1700

Data Index: 7949815 (Open Web Text)

Max Activating Token Index: 215

Text #10

Max Range: 5.3583. Min Range: -5.3583

Max Act: 4.9308. Min Act: -0.1700

Data Index: 7732857 (Open Web Text)

Max Activating Token Index: 827

Text #11

Max Range: 5.3583. Min Range: -5.3583

Max Act: 4.9116. Min Act: -0.1700

Data Index: 7662920 (Open Web Text)

Max Activating Token Index: 270

Text #12

Max Range: 5.3583. Min Range: -5.3583

Max Act: 4.9260. Min Act: -0.1700

Data Index: 2911001 (Open Web Text)

Max Activating Token Index: 940

Text #13

Max Range: 5.3583. Min Range: -5.3583

Max Act: 4.8844. Min Act: -0.1700

Data Index: 146755 (Open Web Text)

Max Activating Token Index: 931

Text #14

Max Range: 5.3583. Min Range: -5.3583

Max Act: 4.8916. Min Act: -0.1700

Data Index: 1057399 (Open Web Text)

Max Activating Token Index: 816

Text #15

Max Range: 5.3583. Min Range: -5.3583

Max Act: 4.8849. Min Act: -0.1700

Data Index: 2758886 (Open Web Text)

Max Activating Token Index: 813

Text #16

Max Range: 5.3583. Min Range: -5.3583

Max Act: 4.8692. Min Act: -0.1700

Data Index: 2633779 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 5.3583. Min Range: -5.3583

Max Act: 4.8545. Min Act: -0.1700

Data Index: 6500567 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 5.3583. Min Range: -5.3583

Max Act: 4.7885. Min Act: -0.1700

Data Index: 3689538 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 5.3583. Min Range: -5.3583

Max Act: 4.8130. Min Act: -0.1700

Data Index: 7131866 (Open Web Text)

Max Activating Token Index: 156