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

Dataset: Open Web Text

Neuron 1895 in Layer 2

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: 4.0669. Min Range: -4.0669

Max Act: 4.0665. Min Act: -0.1700

Data Index: 8673995 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 4.0669. Min Range: -4.0669

Max Act: 4.0669. Min Act: -0.1700

Data Index: 5246801 (Open Web Text)

Max Activating Token Index: 72

Text #2

Max Range: 4.0669. Min Range: -4.0669

Max Act: 4.0610. Min Act: -0.1700

Data Index: 4288102 (Open Web Text)

Max Activating Token Index: 733

Text #3

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.9814. Min Act: -0.1700

Data Index: 3293877 (Open Web Text)

Max Activating Token Index: 114

Text #4

Max Range: 4.0669. Min Range: -4.0669

Max Act: 4.0557. Min Act: -0.1700

Data Index: 4698000 (Open Web Text)

Max Activating Token Index: 911

Text #5

Max Range: 4.0669. Min Range: -4.0669

Max Act: 4.0036. Min Act: -0.1700

Data Index: 4619980 (Open Web Text)

Max Activating Token Index: 517

Text #6

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.9776. Min Act: -0.1700

Data Index: 2198160 (Open Web Text)

Max Activating Token Index: 979

Text #7

Max Range: 4.0669. Min Range: -4.0669

Max Act: 4.0053. Min Act: -0.1700

Data Index: 3649840 (Open Web Text)

Max Activating Token Index: 972

Text #8

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.9854. Min Act: -0.1700

Data Index: 4420069 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.9344. Min Act: -0.1700

Data Index: 3464632 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.9556. Min Act: -0.1700

Data Index: 3027332 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.9323. Min Act: -0.1700

Data Index: 2554237 (Open Web Text)

Max Activating Token Index: 50

Text #12

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.9058. Min Act: -0.1700

Data Index: 7341497 (Open Web Text)

Max Activating Token Index: 976

Text #13

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.8915. Min Act: -0.1700

Data Index: 2622442 (Open Web Text)

Max Activating Token Index: 1016

Text #14

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.8884. Min Act: -0.1700

Data Index: 7723245 (Open Web Text)

Max Activating Token Index: 737

Text #15

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.8881. Min Act: -0.1700

Data Index: 8597475 (Open Web Text)

Max Activating Token Index: 440

Text #16

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.9241. Min Act: -0.1700

Data Index: 70100 (Open Web Text)

Max Activating Token Index: 424

Text #17

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.9171. Min Act: -0.1700

Data Index: 3737757 (Open Web Text)

Max Activating Token Index: 251

Text #18

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.8776. Min Act: -0.1700

Data Index: 899478 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 4.0669. Min Range: -4.0669

Max Act: 3.7799. Min Act: -0.1700

Data Index: 3347615 (Open Web Text)

Max Activating Token Index: 764