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

Dataset: Open Web Text

Neuron 2248 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: 3.0406. Min Range: -3.0406

Max Act: 3.0397. Min Act: -0.1700

Data Index: 6710823 (Open Web Text)

Max Activating Token Index: 594

Text #1

Max Range: 3.0406. Min Range: -3.0406

Max Act: 3.0406. Min Act: -0.1700

Data Index: 3278617 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 3.0406. Min Range: -3.0406

Max Act: 3.0266. Min Act: -0.1700

Data Index: 3278616 (Open Web Text)

Max Activating Token Index: 75

Text #3

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9966. Min Act: -0.1700

Data Index: 602591 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9099. Min Act: -0.1700

Data Index: 4104873 (Open Web Text)

Max Activating Token Index: 330

Text #5

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9007. Min Act: -0.1700

Data Index: 4104868 (Open Web Text)

Max Activating Token Index: 71

Text #6

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9003. Min Act: -0.1700

Data Index: 7786766 (Open Web Text)

Max Activating Token Index: 66

Text #7

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.9049. Min Act: -0.1700

Data Index: 7786773 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8793. Min Act: -0.1700

Data Index: 4104864 (Open Web Text)

Max Activating Token Index: 410

Text #9

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8886. Min Act: -0.1700

Data Index: 4104844 (Open Web Text)

Max Activating Token Index: 209

Text #10

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8821. Min Act: -0.1700

Data Index: 4104856 (Open Web Text)

Max Activating Token Index: 220

Text #11

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8946. Min Act: -0.1700

Data Index: 4104871 (Open Web Text)

Max Activating Token Index: 45

Text #12

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8783. Min Act: -0.1700

Data Index: 4104854 (Open Web Text)

Max Activating Token Index: 175

Text #13

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8799. Min Act: -0.1700

Data Index: 4104852 (Open Web Text)

Max Activating Token Index: 99

Text #14

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8771. Min Act: -0.1700

Data Index: 4104843 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8701. Min Act: -0.1700

Data Index: 4104853 (Open Web Text)

Max Activating Token Index: 475

Text #16

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8675. Min Act: -0.1700

Data Index: 4104862 (Open Web Text)

Max Activating Token Index: 378

Text #17

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8835. Min Act: -0.1700

Data Index: 4104872 (Open Web Text)

Max Activating Token Index: 523

Text #18

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8621. Min Act: -0.1700

Data Index: 4104855 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 3.0406. Min Range: -3.0406

Max Act: 2.8570. Min Act: -0.1700

Data Index: 4104866 (Open Web Text)

Max Activating Token Index: 253