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

Dataset: Open Web Text

Neuron 3061 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: 3.6745. Min Range: -3.6745

Max Act: 3.6745. Min Act: -0.1700

Data Index: 7834249 (Open Web Text)

Max Activating Token Index: 600

Text #1

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.6018. Min Act: -0.1700

Data Index: 875230 (Open Web Text)

Max Activating Token Index: 528

Text #2

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5939. Min Act: -0.1700

Data Index: 2721758 (Open Web Text)

Max Activating Token Index: 841

Text #3

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5382. Min Act: -0.1700

Data Index: 7506409 (Open Web Text)

Max Activating Token Index: 448

Text #4

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5449. Min Act: -0.1700

Data Index: 784311 (Open Web Text)

Max Activating Token Index: 138

Text #5

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5276. Min Act: -0.1700

Data Index: 4586600 (Open Web Text)

Max Activating Token Index: 985

Text #6

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5660. Min Act: -0.1700

Data Index: 806983 (Open Web Text)

Max Activating Token Index: 736

Text #7

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5592. Min Act: -0.1700

Data Index: 7723529 (Open Web Text)

Max Activating Token Index: 612

Text #8

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5429. Min Act: -0.1700

Data Index: 4290782 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5292. Min Act: -0.1700

Data Index: 4880228 (Open Web Text)

Max Activating Token Index: 980

Text #10

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5219. Min Act: -0.1700

Data Index: 3442871 (Open Web Text)

Max Activating Token Index: 37

Text #11

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5165. Min Act: -0.1700

Data Index: 5278108 (Open Web Text)

Max Activating Token Index: 857

Text #12

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5244. Min Act: -0.1700

Data Index: 6767054 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5255. Min Act: -0.1700

Data Index: 3236673 (Open Web Text)

Max Activating Token Index: 297

Text #14

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.5368. Min Act: -0.1700

Data Index: 3946454 (Open Web Text)

Max Activating Token Index: 282

Text #15

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.4891. Min Act: -0.1700

Data Index: 2531525 (Open Web Text)

Max Activating Token Index: 380

Text #16

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.4781. Min Act: -0.1700

Data Index: 4986113 (Open Web Text)

Max Activating Token Index: 484

Text #17

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.4910. Min Act: -0.1700

Data Index: 5637954 (Open Web Text)

Max Activating Token Index: 931

Text #18

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.4527. Min Act: -0.1700

Data Index: 2583876 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 3.6745. Min Range: -3.6745

Max Act: 3.4920. Min Act: -0.1700

Data Index: 6169386 (Open Web Text)

Max Activating Token Index: 587