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

Dataset: Open Web Text

Neuron 895 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: 4.8704. Min Range: -4.8704

Max Act: 4.8693. Min Act: -0.1700

Data Index: 5284569 (Open Web Text)

Max Activating Token Index: 531

Text #1

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.8704. Min Act: -0.1700

Data Index: 2628375 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.8688. Min Act: -0.1700

Data Index: 7776111 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7476. Min Act: -0.1700

Data Index: 8039040 (Open Web Text)

Max Activating Token Index: 530

Text #4

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7629. Min Act: -0.1700

Data Index: 4868294 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7296. Min Act: -0.1700

Data Index: 5991626 (Open Web Text)

Max Activating Token Index: 899

Text #6

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7155. Min Act: -0.1700

Data Index: 8197836 (Open Web Text)

Max Activating Token Index: 409

Text #7

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6752. Min Act: -0.1700

Data Index: 5035278 (Open Web Text)

Max Activating Token Index: 117

Text #8

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7238. Min Act: -0.1700

Data Index: 3397508 (Open Web Text)

Max Activating Token Index: 766

Text #9

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6922. Min Act: -0.1700

Data Index: 146237 (Open Web Text)

Max Activating Token Index: 59

Text #10

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6744. Min Act: -0.1700

Data Index: 7848210 (Open Web Text)

Max Activating Token Index: 394

Text #11

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6572. Min Act: -0.1700

Data Index: 6547041 (Open Web Text)

Max Activating Token Index: 287

Text #12

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6762. Min Act: -0.1700

Data Index: 6742065 (Open Web Text)

Max Activating Token Index: 485

Text #13

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6453. Min Act: -0.1700

Data Index: 6846146 (Open Web Text)

Max Activating Token Index: 49

Text #14

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6223. Min Act: -0.1700

Data Index: 8633525 (Open Web Text)

Max Activating Token Index: 474

Text #15

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6380. Min Act: -0.1700

Data Index: 3766946 (Open Web Text)

Max Activating Token Index: 406

Text #16

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6347. Min Act: -0.1700

Data Index: 5720080 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6379. Min Act: -0.1700

Data Index: 4885748 (Open Web Text)

Max Activating Token Index: 487

Text #18

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.6262. Min Act: -0.1700

Data Index: 4205046 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.5997. Min Act: -0.1700

Data Index: 5665459 (Open Web Text)

Max Activating Token Index: 537