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

Dataset: Open Web Text

Neuron 1408 in Layer 5

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: 3.0152. Min Range: -3.0152

Max Act: 3.0152. Min Act: -0.1700

Data Index: 845265 (Open Web Text)

Max Activating Token Index: 91

Text #1

Max Range: 3.0152. Min Range: -3.0152

Max Act: 3.0013. Min Act: -0.1700

Data Index: 7247613 (Open Web Text)

Max Activating Token Index: 383

Text #2

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9933. Min Act: -0.1700

Data Index: 1495724 (Open Web Text)

Max Activating Token Index: 104

Text #3

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9798. Min Act: -0.1700

Data Index: 600585 (Open Web Text)

Max Activating Token Index: 304

Text #4

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9645. Min Act: -0.1700

Data Index: 1211925 (Open Web Text)

Max Activating Token Index: 232

Text #5

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9437. Min Act: -0.1700

Data Index: 6817323 (Open Web Text)

Max Activating Token Index: 125

Text #6

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9178. Min Act: -0.1700

Data Index: 5603053 (Open Web Text)

Max Activating Token Index: 274

Text #7

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9222. Min Act: -0.1700

Data Index: 7204389 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9285. Min Act: -0.1700

Data Index: 4732407 (Open Web Text)

Max Activating Token Index: 894

Text #9

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9002. Min Act: -0.1700

Data Index: 2021475 (Open Web Text)

Max Activating Token Index: 686

Text #10

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8934. Min Act: -0.1700

Data Index: 6373318 (Open Web Text)

Max Activating Token Index: 1007

Text #11

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8962. Min Act: -0.1700

Data Index: 34459 (Open Web Text)

Max Activating Token Index: 505

Text #12

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8823. Min Act: -0.1700

Data Index: 7974781 (Open Web Text)

Max Activating Token Index: 312

Text #13

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8728. Min Act: -0.1700

Data Index: 1742831 (Open Web Text)

Max Activating Token Index: 696

Text #14

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8527. Min Act: -0.1700

Data Index: 7101266 (Open Web Text)

Max Activating Token Index: 177

Text #15

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8689. Min Act: -0.1700

Data Index: 1374214 (Open Web Text)

Max Activating Token Index: 569

Text #16

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8888. Min Act: -0.1700

Data Index: 4705586 (Open Web Text)

Max Activating Token Index: 993

Text #17

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8563. Min Act: -0.1700

Data Index: 444821 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8586. Min Act: -0.1700

Data Index: 3317974 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8381. Min Act: -0.1700

Data Index: 4976428 (Open Web Text)

Max Activating Token Index: 812