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

Dataset: Open Web Text

Neuron 242 in Layer 6

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: 4.6264. Min Range: -4.6264

Max Act: 4.6264. Min Act: -0.1700

Data Index: 3334304 (Open Web Text)

Max Activating Token Index: 298

Text #1

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.5389. Min Act: -0.1700

Data Index: 933136 (Open Web Text)

Max Activating Token Index: 441

Text #2

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.5078. Min Act: -0.1700

Data Index: 2634037 (Open Web Text)

Max Activating Token Index: 372

Text #3

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4918. Min Act: -0.1700

Data Index: 7634034 (Open Web Text)

Max Activating Token Index: 534

Text #4

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4821. Min Act: -0.1700

Data Index: 648094 (Open Web Text)

Max Activating Token Index: 970

Text #5

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4418. Min Act: -0.1700

Data Index: 4829260 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4385. Min Act: -0.1700

Data Index: 6373473 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4344. Min Act: -0.1700

Data Index: 1185608 (Open Web Text)

Max Activating Token Index: 351

Text #8

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4483. Min Act: -0.1700

Data Index: 6484859 (Open Web Text)

Max Activating Token Index: 351

Text #9

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4547. Min Act: -0.1700

Data Index: 7574239 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4581. Min Act: -0.1700

Data Index: 4420666 (Open Web Text)

Max Activating Token Index: 461

Text #11

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4324. Min Act: -0.1700

Data Index: 2518792 (Open Web Text)

Max Activating Token Index: 655

Text #12

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4061. Min Act: -0.1700

Data Index: 1804298 (Open Web Text)

Max Activating Token Index: 389

Text #13

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4342. Min Act: -0.1700

Data Index: 3806312 (Open Web Text)

Max Activating Token Index: 483

Text #14

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.4213. Min Act: -0.1700

Data Index: 6483492 (Open Web Text)

Max Activating Token Index: 183

Text #15

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.3771. Min Act: -0.1700

Data Index: 4231276 (Open Web Text)

Max Activating Token Index: 936

Text #16

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.3917. Min Act: -0.1700

Data Index: 2568109 (Open Web Text)

Max Activating Token Index: 100

Text #17

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.3701. Min Act: -0.1700

Data Index: 3307723 (Open Web Text)

Max Activating Token Index: 806

Text #18

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.3783. Min Act: -0.1700

Data Index: 567781 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 4.6264. Min Range: -4.6264

Max Act: 4.3578. Min Act: -0.1700

Data Index: 4317765 (Open Web Text)

Max Activating Token Index: 891