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

Dataset: Open Web Text

Neuron 1781 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: 4.7346. Min Range: -4.7346

Max Act: 4.7346. Min Act: -0.1700

Data Index: 3045661 (Open Web Text)

Max Activating Token Index: 965

Text #1

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.6466. Min Act: -0.1700

Data Index: 7867471 (Open Web Text)

Max Activating Token Index: 604

Text #2

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.6239. Min Act: -0.1700

Data Index: 8169818 (Open Web Text)

Max Activating Token Index: 434

Text #3

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.6681. Min Act: -0.1700

Data Index: 8297979 (Open Web Text)

Max Activating Token Index: 489

Text #4

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.5899. Min Act: -0.1700

Data Index: 7588267 (Open Web Text)

Max Activating Token Index: 160

Text #5

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.5816. Min Act: -0.1700

Data Index: 251047 (Open Web Text)

Max Activating Token Index: 579

Text #6

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.5245. Min Act: -0.1700

Data Index: 4946596 (Open Web Text)

Max Activating Token Index: 961

Text #7

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.5539. Min Act: -0.1700

Data Index: 7761913 (Open Web Text)

Max Activating Token Index: 700

Text #8

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.4677. Min Act: -0.1700

Data Index: 6888355 (Open Web Text)

Max Activating Token Index: 671

Text #9

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.5195. Min Act: -0.1700

Data Index: 3269905 (Open Web Text)

Max Activating Token Index: 576

Text #10

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.5410. Min Act: -0.1700

Data Index: 6852091 (Open Web Text)

Max Activating Token Index: 888

Text #11

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.4902. Min Act: -0.1700

Data Index: 5527305 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.4804. Min Act: -0.1700

Data Index: 7295617 (Open Web Text)

Max Activating Token Index: 247

Text #13

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.4114. Min Act: -0.1700

Data Index: 1338476 (Open Web Text)

Max Activating Token Index: 560

Text #14

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.4434. Min Act: -0.1700

Data Index: 4238816 (Open Web Text)

Max Activating Token Index: 925

Text #15

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.4741. Min Act: -0.1700

Data Index: 2297827 (Open Web Text)

Max Activating Token Index: 420

Text #16

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.4517. Min Act: -0.1700

Data Index: 4279204 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.4397. Min Act: -0.1700

Data Index: 3366598 (Open Web Text)

Max Activating Token Index: 244

Text #18

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.4545. Min Act: -0.1700

Data Index: 246536 (Open Web Text)

Max Activating Token Index: 827

Text #19

Max Range: 4.7346. Min Range: -4.7346

Max Act: 4.4839. Min Act: -0.1700

Data Index: 2868373 (Open Web Text)

Max Activating Token Index: 324