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

Dataset: Open Web Text

Neuron 2053 in Layer 4

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: 3.0571. Min Range: -3.0571

Max Act: 3.0571. Min Act: -0.1700

Data Index: 7604349 (Open Web Text)

Max Activating Token Index: 571

Text #1

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.9660. Min Act: -0.1700

Data Index: 7561628 (Open Web Text)

Max Activating Token Index: 65

Text #2

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.9540. Min Act: -0.1700

Data Index: 4729779 (Open Web Text)

Max Activating Token Index: 85

Text #3

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.9554. Min Act: -0.1700

Data Index: 4376653 (Open Web Text)

Max Activating Token Index: 767

Text #4

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.9503. Min Act: -0.1700

Data Index: 2542115 (Open Web Text)

Max Activating Token Index: 333

Text #5

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.9327. Min Act: -0.1700

Data Index: 8628458 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.9224. Min Act: -0.1700

Data Index: 1037840 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.9244. Min Act: -0.1700

Data Index: 8410491 (Open Web Text)

Max Activating Token Index: 558

Text #8

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.8923. Min Act: -0.1700

Data Index: 3887309 (Open Web Text)

Max Activating Token Index: 552

Text #9

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.9085. Min Act: -0.1700

Data Index: 1245871 (Open Web Text)

Max Activating Token Index: 637

Text #10

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.9222. Min Act: -0.1700

Data Index: 7892169 (Open Web Text)

Max Activating Token Index: 255

Text #11

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.9036. Min Act: -0.1700

Data Index: 6468185 (Open Web Text)

Max Activating Token Index: 457

Text #12

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.8972. Min Act: -0.1700

Data Index: 2419964 (Open Web Text)

Max Activating Token Index: 458

Text #13

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.8936. Min Act: -0.1700

Data Index: 4668059 (Open Web Text)

Max Activating Token Index: 179

Text #14

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.8889. Min Act: -0.1700

Data Index: 3083341 (Open Web Text)

Max Activating Token Index: 759

Text #15

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.8943. Min Act: -0.1700

Data Index: 8503379 (Open Web Text)

Max Activating Token Index: 276

Text #16

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.8646. Min Act: -0.1700

Data Index: 1524849 (Open Web Text)

Max Activating Token Index: 702

Text #17

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.8771. Min Act: -0.1700

Data Index: 1831978 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.8813. Min Act: -0.1700

Data Index: 4955917 (Open Web Text)

Max Activating Token Index: 317

Text #19

Max Range: 3.0571. Min Range: -3.0571

Max Act: 2.8476. Min Act: -0.1700

Data Index: 5003782 (Open Web Text)

Max Activating Token Index: 528