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

Dataset: Open Web Text

Neuron 2072 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: 3.7591. Min Range: -3.7591

Max Act: 3.7591. Min Act: -0.1700

Data Index: 5563851 (Open Web Text)

Max Activating Token Index: 856

Text #1

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.6599. Min Act: -0.1700

Data Index: 6494546 (Open Web Text)

Max Activating Token Index: 704

Text #2

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.6543. Min Act: -0.1700

Data Index: 380604 (Open Web Text)

Max Activating Token Index: 413

Text #3

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.6443. Min Act: -0.1700

Data Index: 5946572 (Open Web Text)

Max Activating Token Index: 747

Text #4

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.6194. Min Act: -0.1700

Data Index: 1153845 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.6246. Min Act: -0.1700

Data Index: 6285044 (Open Web Text)

Max Activating Token Index: 123

Text #6

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.6269. Min Act: -0.1700

Data Index: 5374837 (Open Web Text)

Max Activating Token Index: 307

Text #7

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.6157. Min Act: -0.1700

Data Index: 6333014 (Open Web Text)

Max Activating Token Index: 530

Text #8

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.6202. Min Act: -0.1700

Data Index: 4943519 (Open Web Text)

Max Activating Token Index: 924

Text #9

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5940. Min Act: -0.1700

Data Index: 3308573 (Open Web Text)

Max Activating Token Index: 818

Text #10

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5903. Min Act: -0.1700

Data Index: 424143 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5775. Min Act: -0.1700

Data Index: 3947227 (Open Web Text)

Max Activating Token Index: 1015

Text #12

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5903. Min Act: -0.1700

Data Index: 694750 (Open Web Text)

Max Activating Token Index: 320

Text #13

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5826. Min Act: -0.1700

Data Index: 6963038 (Open Web Text)

Max Activating Token Index: 1014

Text #14

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5843. Min Act: -0.1700

Data Index: 2967845 (Open Web Text)

Max Activating Token Index: 396

Text #15

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5531. Min Act: -0.1700

Data Index: 1927905 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5903. Min Act: -0.1700

Data Index: 1102763 (Open Web Text)

Max Activating Token Index: 679

Text #17

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5621. Min Act: -0.1700

Data Index: 5308012 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5520. Min Act: -0.1700

Data Index: 5343692 (Open Web Text)

Max Activating Token Index: 650

Text #19

Max Range: 3.7591. Min Range: -3.7591

Max Act: 3.5457. Min Act: -0.1700

Data Index: 3592120 (Open Web Text)

Max Activating Token Index: 157