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

Dataset: Open Web Text

Neuron 585 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: 4.5506. Min Range: -4.5506

Max Act: 4.5506. Min Act: -0.1700

Data Index: 6673308 (Open Web Text)

Max Activating Token Index: 98

Text #1

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.4787. Min Act: -0.1700

Data Index: 1525573 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.4263. Min Act: -0.1700

Data Index: 7555830 (Open Web Text)

Max Activating Token Index: 671

Text #3

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3998. Min Act: -0.1700

Data Index: 6661285 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3953. Min Act: -0.1700

Data Index: 6229726 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3861. Min Act: -0.1700

Data Index: 2840770 (Open Web Text)

Max Activating Token Index: 345

Text #6

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3775. Min Act: -0.1700

Data Index: 4543305 (Open Web Text)

Max Activating Token Index: 875

Text #7

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3448. Min Act: -0.1700

Data Index: 1273649 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3236. Min Act: -0.1700

Data Index: 5062823 (Open Web Text)

Max Activating Token Index: 886

Text #9

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3558. Min Act: -0.1700

Data Index: 6877028 (Open Web Text)

Max Activating Token Index: 513

Text #10

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3480. Min Act: -0.1700

Data Index: 1778961 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3483. Min Act: -0.1700

Data Index: 4967539 (Open Web Text)

Max Activating Token Index: 181

Text #12

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3475. Min Act: -0.1700

Data Index: 6388120 (Open Web Text)

Max Activating Token Index: 298

Text #13

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3436. Min Act: -0.1700

Data Index: 7660155 (Open Web Text)

Max Activating Token Index: 355

Text #14

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3595. Min Act: -0.1700

Data Index: 2779724 (Open Web Text)

Max Activating Token Index: 836

Text #15

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3516. Min Act: -0.1700

Data Index: 7393239 (Open Web Text)

Max Activating Token Index: 119

Text #16

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3045. Min Act: -0.1700

Data Index: 1116362 (Open Web Text)

Max Activating Token Index: 450

Text #17

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3022. Min Act: -0.1700

Data Index: 3472481 (Open Web Text)

Max Activating Token Index: 246

Text #18

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3167. Min Act: -0.1700

Data Index: 6871558 (Open Web Text)

Max Activating Token Index: 453

Text #19

Max Range: 4.5506. Min Range: -4.5506

Max Act: 4.3224. Min Act: -0.1700

Data Index: 7222687 (Open Web Text)

Max Activating Token Index: 70