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

Dataset: Open Web Text

Neuron 3020 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: 4.3298. Min Range: -4.3298

Max Act: 4.3298. Min Act: -0.1700

Data Index: 6368433 (Open Web Text)

Max Activating Token Index: 280

Text #1

Max Range: 4.3298. Min Range: -4.3298

Max Act: 4.2855. Min Act: -0.1700

Data Index: 4051615 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 4.3298. Min Range: -4.3298

Max Act: 4.1116. Min Act: -0.1700

Data Index: 6436164 (Open Web Text)

Max Activating Token Index: 818

Text #3

Max Range: 4.3298. Min Range: -4.3298

Max Act: 4.1098. Min Act: -0.1700

Data Index: 6310518 (Open Web Text)

Max Activating Token Index: 800

Text #4

Max Range: 4.3298. Min Range: -4.3298

Max Act: 4.1015. Min Act: -0.1700

Data Index: 4937139 (Open Web Text)

Max Activating Token Index: 453

Text #5

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.9821. Min Act: -0.1700

Data Index: 2419136 (Open Web Text)

Max Activating Token Index: 752

Text #6

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.9093. Min Act: -0.1700

Data Index: 2825929 (Open Web Text)

Max Activating Token Index: 748

Text #7

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.9262. Min Act: -0.1700

Data Index: 4213628 (Open Web Text)

Max Activating Token Index: 413

Text #8

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.9370. Min Act: -0.1700

Data Index: 3670149 (Open Web Text)

Max Activating Token Index: 399

Text #9

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.8837. Min Act: -0.1700

Data Index: 6366099 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.8811. Min Act: -0.1700

Data Index: 373262 (Open Web Text)

Max Activating Token Index: 671

Text #11

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.8838. Min Act: -0.1700

Data Index: 670589 (Open Web Text)

Max Activating Token Index: 994

Text #12

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.9209. Min Act: -0.1700

Data Index: 736394 (Open Web Text)

Max Activating Token Index: 828

Text #13

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.8677. Min Act: -0.1700

Data Index: 4237554 (Open Web Text)

Max Activating Token Index: 1018

Text #14

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.8543. Min Act: -0.1700

Data Index: 2148218 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.8721. Min Act: -0.1700

Data Index: 7255549 (Open Web Text)

Max Activating Token Index: 858

Text #16

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.8852. Min Act: -0.1700

Data Index: 394604 (Open Web Text)

Max Activating Token Index: 865

Text #17

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.8289. Min Act: -0.1700

Data Index: 372846 (Open Web Text)

Max Activating Token Index: 156

Text #18

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.8282. Min Act: -0.1700

Data Index: 1082905 (Open Web Text)

Max Activating Token Index: 392

Text #19

Max Range: 4.3298. Min Range: -4.3298

Max Act: 3.8216. Min Act: -0.1700

Data Index: 1086719 (Open Web Text)

Max Activating Token Index: 108