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

Dataset: Open Web Text

Neuron 1945 in Layer 0

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: 1.4754. Min Range: -1.4754

Max Act: 1.4754. Min Act: -0.0193

Data Index: 7408265 (Open Web Text)

Max Activating Token Index: 91

Text #1

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.4576. Min Act: -0.0193

Data Index: 8435071 (Open Web Text)

Max Activating Token Index: 744

Text #2

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.4454. Min Act: -0.0682

Data Index: 2174535 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.4124. Min Act: -0.0533

Data Index: 2245877 (Open Web Text)

Max Activating Token Index: 153

Text #4

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.4043. Min Act: -0.0805

Data Index: 7408264 (Open Web Text)

Max Activating Token Index: 137

Text #5

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3829. Min Act: -0.0644

Data Index: 4016583 (Open Web Text)

Max Activating Token Index: 352

Text #6

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3894. Min Act: -0.0193

Data Index: 8502037 (Open Web Text)

Max Activating Token Index: 333

Text #7

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3845. Min Act: -0.0306

Data Index: 5062390 (Open Web Text)

Max Activating Token Index: 102

Text #8

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3862. Min Act: -0.0193

Data Index: 3095815 (Open Web Text)

Max Activating Token Index: 403

Text #9

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3802. Min Act: -0.0565

Data Index: 5325845 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3774. Min Act: -0.0616

Data Index: 4926836 (Open Web Text)

Max Activating Token Index: 176

Text #11

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3719. Min Act: -0.0461

Data Index: 5203371 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3614. Min Act: -0.0207

Data Index: 6551126 (Open Web Text)

Max Activating Token Index: 98

Text #13

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3664. Min Act: -0.0193

Data Index: 2851624 (Open Web Text)

Max Activating Token Index: 192

Text #14

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3651. Min Act: -0.0505

Data Index: 7213298 (Open Web Text)

Max Activating Token Index: 529

Text #15

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3579. Min Act: -0.0922

Data Index: 5259309 (Open Web Text)

Max Activating Token Index: 332

Text #16

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3528. Min Act: -0.0313

Data Index: 880708 (Open Web Text)

Max Activating Token Index: 117

Text #17

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3568. Min Act: -0.0193

Data Index: 2729960 (Open Web Text)

Max Activating Token Index: 166

Text #18

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3626. Min Act: -0.0193

Data Index: 7206816 (Open Web Text)

Max Activating Token Index: 395

Text #19

Max Range: 1.4754. Min Range: -1.4754

Max Act: 1.3631. Min Act: -0.0193

Data Index: 6579554 (Open Web Text)

Max Activating Token Index: 445