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

Dataset: Open Web Text

Neuron 271 in Layer 6

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: 7.1197. Min Range: -7.1197

Max Act: 7.1197. Min Act: -0.1700

Data Index: 7176891 (Open Web Text)

Max Activating Token Index: 251

Text #1

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.7059. Min Act: -0.1700

Data Index: 8607328 (Open Web Text)

Max Activating Token Index: 679

Text #2

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.5097. Min Act: -0.1700

Data Index: 6533404 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.4637. Min Act: -0.1700

Data Index: 2823190 (Open Web Text)

Max Activating Token Index: 193

Text #4

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.3979. Min Act: -0.1700

Data Index: 3795108 (Open Web Text)

Max Activating Token Index: 707

Text #5

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.4212. Min Act: -0.1700

Data Index: 5281155 (Open Web Text)

Max Activating Token Index: 860

Text #6

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.3701. Min Act: -0.1700

Data Index: 8689613 (Open Web Text)

Max Activating Token Index: 691

Text #7

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.3640. Min Act: -0.1700

Data Index: 7675451 (Open Web Text)

Max Activating Token Index: 194

Text #8

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.3629. Min Act: -0.1700

Data Index: 5556472 (Open Web Text)

Max Activating Token Index: 989

Text #9

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.3418. Min Act: -0.1700

Data Index: 6967377 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.3221. Min Act: -0.1700

Data Index: 878081 (Open Web Text)

Max Activating Token Index: 178

Text #11

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.3496. Min Act: -0.1700

Data Index: 3367714 (Open Web Text)

Max Activating Token Index: 334

Text #12

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.3157. Min Act: -0.1700

Data Index: 6704796 (Open Web Text)

Max Activating Token Index: 121

Text #13

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.2959. Min Act: -0.1700

Data Index: 4847852 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.2777. Min Act: -0.1700

Data Index: 5624021 (Open Web Text)

Max Activating Token Index: 92

Text #15

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.2082. Min Act: -0.1700

Data Index: 2872370 (Open Web Text)

Max Activating Token Index: 926

Text #16

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.2456. Min Act: -0.1700

Data Index: 2700440 (Open Web Text)

Max Activating Token Index: 714

Text #17

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.2014. Min Act: -0.1700

Data Index: 8068800 (Open Web Text)

Max Activating Token Index: 408

Text #18

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.1491. Min Act: -0.1700

Data Index: 1739691 (Open Web Text)

Max Activating Token Index: 984

Text #19

Max Range: 7.1197. Min Range: -7.1197

Max Act: 6.2087. Min Act: -0.1700

Data Index: 7362951 (Open Web Text)

Max Activating Token Index: 236