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

Dataset: Open Web Text

Neuron 1008 in Layer 4

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: 4.1297. Min Range: -4.1297

Max Act: 4.1297. Min Act: -0.1700

Data Index: 771810 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 4.1297. Min Range: -4.1297

Max Act: 4.0987. Min Act: -0.1700

Data Index: 4375775 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.9690. Min Act: -0.1700

Data Index: 562950 (Open Web Text)

Max Activating Token Index: 159

Text #3

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.9952. Min Act: -0.1700

Data Index: 1842045 (Open Web Text)

Max Activating Token Index: 752

Text #4

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.9606. Min Act: -0.1700

Data Index: 1590280 (Open Web Text)

Max Activating Token Index: 864

Text #5

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.9551. Min Act: -0.1700

Data Index: 2218680 (Open Web Text)

Max Activating Token Index: 648

Text #6

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.9112. Min Act: -0.1700

Data Index: 4357022 (Open Web Text)

Max Activating Token Index: 532

Text #7

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.9417. Min Act: -0.1700

Data Index: 4436982 (Open Web Text)

Max Activating Token Index: 399

Text #8

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.9212. Min Act: -0.1700

Data Index: 246980 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.8683. Min Act: -0.1700

Data Index: 2091584 (Open Web Text)

Max Activating Token Index: 851

Text #10

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.9022. Min Act: -0.1700

Data Index: 511433 (Open Web Text)

Max Activating Token Index: 247

Text #11

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.8606. Min Act: -0.1700

Data Index: 5960304 (Open Web Text)

Max Activating Token Index: 399

Text #12

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.8788. Min Act: -0.1700

Data Index: 1504598 (Open Web Text)

Max Activating Token Index: 44

Text #13

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.8750. Min Act: -0.1700

Data Index: 8589519 (Open Web Text)

Max Activating Token Index: 147

Text #14

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.8600. Min Act: -0.1700

Data Index: 2614846 (Open Web Text)

Max Activating Token Index: 546

Text #15

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.8779. Min Act: -0.1700

Data Index: 3733262 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.8598. Min Act: -0.1700

Data Index: 96637 (Open Web Text)

Max Activating Token Index: 555

Text #17

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.8642. Min Act: -0.1700

Data Index: 3746319 (Open Web Text)

Max Activating Token Index: 871

Text #18

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.8495. Min Act: -0.1700

Data Index: 2071330 (Open Web Text)

Max Activating Token Index: 600

Text #19

Max Range: 4.1297. Min Range: -4.1297

Max Act: 3.8637. Min Act: -0.1700

Data Index: 1548491 (Open Web Text)

Max Activating Token Index: 179