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

Dataset: Open Web Text

Neuron 2912 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: 3.0989. Min Range: -3.0989

Max Act: 3.0989. Min Act: -0.1700

Data Index: 7600568 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0418. Min Act: -0.1700

Data Index: 1001635 (Open Web Text)

Max Activating Token Index: 836

Text #2

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0660. Min Act: -0.1700

Data Index: 1269844 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0018. Min Act: -0.1700

Data Index: 2645432 (Open Web Text)

Max Activating Token Index: 460

Text #4

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9875. Min Act: -0.1700

Data Index: 5365995 (Open Web Text)

Max Activating Token Index: 675

Text #5

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9995. Min Act: -0.1700

Data Index: 6716796 (Open Web Text)

Max Activating Token Index: 946

Text #6

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9711. Min Act: -0.1700

Data Index: 3253473 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9974. Min Act: -0.1700

Data Index: 5173316 (Open Web Text)

Max Activating Token Index: 842

Text #8

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9688. Min Act: -0.1700

Data Index: 5569617 (Open Web Text)

Max Activating Token Index: 96

Text #9

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9221. Min Act: -0.1700

Data Index: 1411600 (Open Web Text)

Max Activating Token Index: 409

Text #10

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9054. Min Act: -0.1700

Data Index: 1708982 (Open Web Text)

Max Activating Token Index: 396

Text #11

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9206. Min Act: -0.1700

Data Index: 4478979 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9337. Min Act: -0.1700

Data Index: 4379609 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9166. Min Act: -0.1700

Data Index: 3787786 (Open Web Text)

Max Activating Token Index: 738

Text #14

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9029. Min Act: -0.1700

Data Index: 3499629 (Open Web Text)

Max Activating Token Index: 990

Text #15

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9227. Min Act: -0.1700

Data Index: 7206034 (Open Web Text)

Max Activating Token Index: 817

Text #16

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9302. Min Act: -0.1700

Data Index: 4520301 (Open Web Text)

Max Activating Token Index: 600

Text #17

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9248. Min Act: -0.1700

Data Index: 1647881 (Open Web Text)

Max Activating Token Index: 455

Text #18

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9109. Min Act: -0.1700

Data Index: 4454876 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9116. Min Act: -0.1700

Data Index: 2650707 (Open Web Text)

Max Activating Token Index: 944