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

Dataset: Open Web Text

Neuron 2851 in Layer 2

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: 4.4690. Min Range: -4.4690

Max Act: 4.4690. Min Act: -0.1700

Data Index: 6405445 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.4256. Min Act: -0.1700

Data Index: 4526571 (Open Web Text)

Max Activating Token Index: 711

Text #2

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3947. Min Act: -0.1700

Data Index: 6128958 (Open Web Text)

Max Activating Token Index: 764

Text #3

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3983. Min Act: -0.1700

Data Index: 7760532 (Open Web Text)

Max Activating Token Index: 536

Text #4

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.4080. Min Act: -0.1700

Data Index: 1896142 (Open Web Text)

Max Activating Token Index: 736

Text #5

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.4039. Min Act: -0.1700

Data Index: 1473865 (Open Web Text)

Max Activating Token Index: 390

Text #6

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3779. Min Act: -0.1700

Data Index: 874781 (Open Web Text)

Max Activating Token Index: 964

Text #7

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3828. Min Act: -0.1700

Data Index: 53703 (Open Web Text)

Max Activating Token Index: 468

Text #8

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3684. Min Act: -0.1700

Data Index: 1795596 (Open Web Text)

Max Activating Token Index: 406

Text #9

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3700. Min Act: -0.1700

Data Index: 2615182 (Open Web Text)

Max Activating Token Index: 231

Text #10

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3682. Min Act: -0.1700

Data Index: 4685967 (Open Web Text)

Max Activating Token Index: 88

Text #11

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3425. Min Act: -0.1700

Data Index: 5394525 (Open Web Text)

Max Activating Token Index: 979

Text #12

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3430. Min Act: -0.1700

Data Index: 5056740 (Open Web Text)

Max Activating Token Index: 539

Text #13

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3246. Min Act: -0.1700

Data Index: 4986652 (Open Web Text)

Max Activating Token Index: 844

Text #14

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3066. Min Act: -0.1700

Data Index: 3423164 (Open Web Text)

Max Activating Token Index: 546

Text #15

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3353. Min Act: -0.1700

Data Index: 4506576 (Open Web Text)

Max Activating Token Index: 147

Text #16

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3359. Min Act: -0.1700

Data Index: 4501234 (Open Web Text)

Max Activating Token Index: 158

Text #17

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3390. Min Act: -0.1700

Data Index: 4361280 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3290. Min Act: -0.1700

Data Index: 2783493 (Open Web Text)

Max Activating Token Index: 335

Text #19

Max Range: 4.4690. Min Range: -4.4690

Max Act: 4.3152. Min Act: -0.1700

Data Index: 2648351 (Open Web Text)

Max Activating Token Index: 494