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

Dataset: Open Web Text

Neuron 2883 in Layer 3

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: 3.8506. Min Range: -3.8506

Max Act: 3.8424. Min Act: -0.1700

Data Index: 6994847 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8098. Min Act: -0.1700

Data Index: 5864847 (Open Web Text)

Max Activating Token Index: 646

Text #2

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8506. Min Act: -0.1700

Data Index: 721686 (Open Web Text)

Max Activating Token Index: 127

Text #3

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7851. Min Act: -0.1700

Data Index: 2522622 (Open Web Text)

Max Activating Token Index: 413

Text #4

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8210. Min Act: -0.1700

Data Index: 7810067 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.8080. Min Act: -0.1700

Data Index: 6953507 (Open Web Text)

Max Activating Token Index: 930

Text #6

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7752. Min Act: -0.1700

Data Index: 8559263 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7593. Min Act: -0.1700

Data Index: 239503 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7318. Min Act: -0.1700

Data Index: 4594400 (Open Web Text)

Max Activating Token Index: 875

Text #9

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7069. Min Act: -0.1700

Data Index: 5784052 (Open Web Text)

Max Activating Token Index: 476

Text #10

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7180. Min Act: -0.1700

Data Index: 8684591 (Open Web Text)

Max Activating Token Index: 980

Text #11

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.7269. Min Act: -0.1700

Data Index: 4269438 (Open Web Text)

Max Activating Token Index: 412

Text #12

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.6887. Min Act: -0.1700

Data Index: 2002323 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.6212. Min Act: -0.1700

Data Index: 343795 (Open Web Text)

Max Activating Token Index: 909

Text #14

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.6563. Min Act: -0.1700

Data Index: 334970 (Open Web Text)

Max Activating Token Index: 276

Text #15

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.6324. Min Act: -0.1700

Data Index: 2508171 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.6413. Min Act: -0.1700

Data Index: 3152938 (Open Web Text)

Max Activating Token Index: 497

Text #17

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.6554. Min Act: -0.1700

Data Index: 3672671 (Open Web Text)

Max Activating Token Index: 254

Text #18

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.6539. Min Act: -0.1700

Data Index: 3323321 (Open Web Text)

Max Activating Token Index: 313

Text #19

Max Range: 3.8506. Min Range: -3.8506

Max Act: 3.6414. Min Act: -0.1700

Data Index: 1510558 (Open Web Text)

Max Activating Token Index: 328