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

Dataset: Open Web Text

Neuron 246 in Layer 4

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: 4.5563. Min Range: -4.5563

Max Act: 4.5388. Min Act: -0.1700

Data Index: 5321316 (Open Web Text)

Max Activating Token Index: 831

Text #1

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.5563. Min Act: -0.1700

Data Index: 7794480 (Open Web Text)

Max Activating Token Index: 732

Text #2

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.5378. Min Act: -0.1700

Data Index: 7950478 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.5263. Min Act: -0.1700

Data Index: 7904820 (Open Web Text)

Max Activating Token Index: 251

Text #4

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.4850. Min Act: -0.1700

Data Index: 5440145 (Open Web Text)

Max Activating Token Index: 531

Text #5

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.4447. Min Act: -0.1700

Data Index: 8695607 (Open Web Text)

Max Activating Token Index: 758

Text #6

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.4061. Min Act: -0.1700

Data Index: 7087359 (Open Web Text)

Max Activating Token Index: 956

Text #7

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.4269. Min Act: -0.1700

Data Index: 2745365 (Open Web Text)

Max Activating Token Index: 130

Text #8

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.4020. Min Act: -0.1700

Data Index: 7623104 (Open Web Text)

Max Activating Token Index: 1002

Text #9

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.4802. Min Act: -0.1700

Data Index: 3199735 (Open Web Text)

Max Activating Token Index: 889

Text #10

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.4138. Min Act: -0.1700

Data Index: 7023653 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.3688. Min Act: -0.1700

Data Index: 8144263 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.4159. Min Act: -0.1700

Data Index: 3799325 (Open Web Text)

Max Activating Token Index: 947

Text #13

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.3637. Min Act: -0.1700

Data Index: 6411126 (Open Web Text)

Max Activating Token Index: 872

Text #14

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.4624. Min Act: -0.1700

Data Index: 1154484 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.3654. Min Act: -0.1700

Data Index: 4023770 (Open Web Text)

Max Activating Token Index: 57

Text #16

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.3509. Min Act: -0.1700

Data Index: 4065512 (Open Web Text)

Max Activating Token Index: 248

Text #17

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.3784. Min Act: -0.1700

Data Index: 2290728 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.3767. Min Act: -0.1700

Data Index: 7613449 (Open Web Text)

Max Activating Token Index: 109

Text #19

Max Range: 4.5563. Min Range: -4.5563

Max Act: 4.4147. Min Act: -0.1700

Data Index: 4703797 (Open Web Text)

Max Activating Token Index: 395