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

Dataset: Open Web Text

Neuron 3057 in Layer 1

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: 1.9126. Min Range: -1.9126

Max Act: 1.9075. Min Act: -0.1700

Data Index: 4946579 (Open Web Text)

Max Activating Token Index: 498

Text #1

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.9126. Min Act: -0.1700

Data Index: 3492723 (Open Web Text)

Max Activating Token Index: 805

Text #2

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.9009. Min Act: -0.1700

Data Index: 2388031 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8887. Min Act: -0.1700

Data Index: 4613828 (Open Web Text)

Max Activating Token Index: 637

Text #4

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8957. Min Act: -0.1700

Data Index: 4182869 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8963. Min Act: -0.1700

Data Index: 2497463 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8819. Min Act: -0.1700

Data Index: 3910322 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8579. Min Act: -0.1700

Data Index: 4750062 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8562. Min Act: -0.1700

Data Index: 3230627 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8704. Min Act: -0.1700

Data Index: 5860665 (Open Web Text)

Max Activating Token Index: 168

Text #10

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8624. Min Act: -0.1700

Data Index: 2327250 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8462. Min Act: -0.1700

Data Index: 7360736 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8404. Min Act: -0.1700

Data Index: 2981207 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8321. Min Act: -0.1700

Data Index: 4663040 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8322. Min Act: -0.1700

Data Index: 4497016 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8531. Min Act: -0.1700

Data Index: 8533600 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8302. Min Act: -0.1700

Data Index: 227378 (Open Web Text)

Max Activating Token Index: 840

Text #17

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8400. Min Act: -0.1700

Data Index: 1908209 (Open Web Text)

Max Activating Token Index: 444

Text #18

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8444. Min Act: -0.1700

Data Index: 695441 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.9126. Min Range: -1.9126

Max Act: 1.8478. Min Act: -0.1700

Data Index: 3110249 (Open Web Text)

Max Activating Token Index: 212