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

Dataset: Open Web Text

Neuron 920 in Layer 6

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: 3.6243. Min Range: -3.6243

Max Act: 3.6219. Min Act: -0.1700

Data Index: 4735037 (Open Web Text)

Max Activating Token Index: 424

Text #1

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.6243. Min Act: -0.1700

Data Index: 1761649 (Open Web Text)

Max Activating Token Index: 229

Text #2

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.5983. Min Act: -0.1700

Data Index: 3553405 (Open Web Text)

Max Activating Token Index: 275

Text #3

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.5492. Min Act: -0.1700

Data Index: 7685013 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.5282. Min Act: -0.1700

Data Index: 7140856 (Open Web Text)

Max Activating Token Index: 625

Text #5

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.5028. Min Act: -0.1700

Data Index: 8097375 (Open Web Text)

Max Activating Token Index: 709

Text #6

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.5212. Min Act: -0.1700

Data Index: 7174910 (Open Web Text)

Max Activating Token Index: 732

Text #7

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.5273. Min Act: -0.1700

Data Index: 5405788 (Open Web Text)

Max Activating Token Index: 497

Text #8

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.5012. Min Act: -0.1700

Data Index: 7685011 (Open Web Text)

Max Activating Token Index: 57

Text #9

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4708. Min Act: -0.1700

Data Index: 5485964 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4576. Min Act: -0.1700

Data Index: 3510023 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4633. Min Act: -0.1700

Data Index: 1375995 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4574. Min Act: -0.1700

Data Index: 2710654 (Open Web Text)

Max Activating Token Index: 781

Text #13

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4549. Min Act: -0.1700

Data Index: 4803611 (Open Web Text)

Max Activating Token Index: 966

Text #14

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4752. Min Act: -0.1700

Data Index: 588421 (Open Web Text)

Max Activating Token Index: 542

Text #15

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4559. Min Act: -0.1700

Data Index: 3328142 (Open Web Text)

Max Activating Token Index: 432

Text #16

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4516. Min Act: -0.1700

Data Index: 5864979 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4156. Min Act: -0.1700

Data Index: 2945979 (Open Web Text)

Max Activating Token Index: 664

Text #18

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4475. Min Act: -0.1700

Data Index: 3326040 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 3.6243. Min Range: -3.6243

Max Act: 3.4250. Min Act: -0.1700

Data Index: 6902284 (Open Web Text)

Max Activating Token Index: 881