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

Dataset: Open Web Text

Neuron 1799 in Layer 0

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: 1.4529. Min Range: -1.4529

Max Act: 1.4529. Min Act: -0.1700

Data Index: 4917683 (Open Web Text)

Max Activating Token Index: 37

Text #1

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.4189. Min Act: -0.1700

Data Index: 8593576 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.4142. Min Act: -0.1700

Data Index: 7296114 (Open Web Text)

Max Activating Token Index: 253

Text #3

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.4087. Min Act: -0.1700

Data Index: 5850363 (Open Web Text)

Max Activating Token Index: 442

Text #4

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3973. Min Act: -0.1700

Data Index: 6493602 (Open Web Text)

Max Activating Token Index: 360

Text #5

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3943. Min Act: -0.1700

Data Index: 6248346 (Open Web Text)

Max Activating Token Index: 395

Text #6

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3491. Min Act: -0.1700

Data Index: 1680282 (Open Web Text)

Max Activating Token Index: 306

Text #7

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3315. Min Act: -0.1700

Data Index: 2250422 (Open Web Text)

Max Activating Token Index: 476

Text #8

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3428. Min Act: -0.1700

Data Index: 2130701 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3465. Min Act: -0.1700

Data Index: 7006741 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3404. Min Act: -0.1700

Data Index: 3865586 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3271. Min Act: -0.1700

Data Index: 2793531 (Open Web Text)

Max Activating Token Index: 661

Text #12

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3227. Min Act: -0.1700

Data Index: 1940219 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3274. Min Act: -0.1700

Data Index: 2346163 (Open Web Text)

Max Activating Token Index: 159

Text #14

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3309. Min Act: -0.1700

Data Index: 6493613 (Open Web Text)

Max Activating Token Index: 41

Text #15

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3056. Min Act: -0.1700

Data Index: 3982073 (Open Web Text)

Max Activating Token Index: 917

Text #16

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3031. Min Act: -0.1700

Data Index: 5551404 (Open Web Text)

Max Activating Token Index: 751

Text #17

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3097. Min Act: -0.1700

Data Index: 1850890 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3055. Min Act: -0.1700

Data Index: 3941873 (Open Web Text)

Max Activating Token Index: 384

Text #19

Max Range: 1.4529. Min Range: -1.4529

Max Act: 1.3142. Min Act: -0.1700

Data Index: 6327789 (Open Web Text)

Max Activating Token Index: 433