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

Dataset: Open Web Text

Neuron 712 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: 4.9293. Min Range: -4.9293

Max Act: 4.9293. Min Act: -0.1700

Data Index: 8787930 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.8285. Min Act: -0.1700

Data Index: 2945134 (Open Web Text)

Max Activating Token Index: 135

Text #2

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.7293. Min Act: -0.1700

Data Index: 1506377 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.7504. Min Act: -0.1700

Data Index: 4312954 (Open Web Text)

Max Activating Token Index: 55

Text #4

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.7621. Min Act: -0.1700

Data Index: 1245953 (Open Web Text)

Max Activating Token Index: 268

Text #5

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.7337. Min Act: -0.1700

Data Index: 7043290 (Open Web Text)

Max Activating Token Index: 892

Text #6

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.6852. Min Act: -0.1700

Data Index: 6028762 (Open Web Text)

Max Activating Token Index: 105

Text #7

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.7188. Min Act: -0.1700

Data Index: 5711056 (Open Web Text)

Max Activating Token Index: 570

Text #8

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.7478. Min Act: -0.1700

Data Index: 3952877 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.6753. Min Act: -0.1700

Data Index: 4871422 (Open Web Text)

Max Activating Token Index: 452

Text #10

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.7140. Min Act: -0.1700

Data Index: 668623 (Open Web Text)

Max Activating Token Index: 312

Text #11

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.6965. Min Act: -0.1700

Data Index: 2945133 (Open Web Text)

Max Activating Token Index: 978

Text #12

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.7192. Min Act: -0.1700

Data Index: 978874 (Open Web Text)

Max Activating Token Index: 401

Text #13

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.7009. Min Act: -0.1700

Data Index: 8661082 (Open Web Text)

Max Activating Token Index: 179

Text #14

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.6969. Min Act: -0.1700

Data Index: 2854549 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.6682. Min Act: -0.1700

Data Index: 3398047 (Open Web Text)

Max Activating Token Index: 614

Text #16

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.6066. Min Act: -0.1700

Data Index: 4332285 (Open Web Text)

Max Activating Token Index: 177

Text #17

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.6845. Min Act: -0.1700

Data Index: 5446375 (Open Web Text)

Max Activating Token Index: 92

Text #18

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.6397. Min Act: -0.1700

Data Index: 5595299 (Open Web Text)

Max Activating Token Index: 377

Text #19

Max Range: 4.9293. Min Range: -4.9293

Max Act: 4.5983. Min Act: -0.1700

Data Index: 8092599 (Open Web Text)

Max Activating Token Index: 276