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

Dataset: Open Web Text

Neuron 1781 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: 4.5021. Min Range: -4.5021

Max Act: 4.5021. Min Act: -0.1700

Data Index: 6643213 (Open Web Text)

Max Activating Token Index: 742

Text #1

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.2799. Min Act: -0.1700

Data Index: 7226141 (Open Web Text)

Max Activating Token Index: 686

Text #2

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.1955. Min Act: -0.1700

Data Index: 7885897 (Open Web Text)

Max Activating Token Index: 634

Text #3

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.1807. Min Act: -0.1700

Data Index: 5942335 (Open Web Text)

Max Activating Token Index: 656

Text #4

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.1706. Min Act: -0.1700

Data Index: 8819974 (Open Web Text)

Max Activating Token Index: 383

Text #5

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.1920. Min Act: -0.1700

Data Index: 6764453 (Open Web Text)

Max Activating Token Index: 362

Text #6

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.1463. Min Act: -0.1700

Data Index: 5748759 (Open Web Text)

Max Activating Token Index: 430

Text #7

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.1631. Min Act: -0.1700

Data Index: 1093812 (Open Web Text)

Max Activating Token Index: 249

Text #8

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.1212. Min Act: -0.1700

Data Index: 2680003 (Open Web Text)

Max Activating Token Index: 284

Text #9

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.1160. Min Act: -0.1700

Data Index: 1778741 (Open Web Text)

Max Activating Token Index: 83

Text #10

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.0843. Min Act: -0.1700

Data Index: 6893662 (Open Web Text)

Max Activating Token Index: 299

Text #11

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.0933. Min Act: -0.1700

Data Index: 2797590 (Open Web Text)

Max Activating Token Index: 296

Text #12

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.0688. Min Act: -0.1700

Data Index: 1596141 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.1119. Min Act: -0.1700

Data Index: 2617411 (Open Web Text)

Max Activating Token Index: 924

Text #14

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.0887. Min Act: -0.1700

Data Index: 6611118 (Open Web Text)

Max Activating Token Index: 419

Text #15

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.0872. Min Act: -0.1700

Data Index: 4823505 (Open Web Text)

Max Activating Token Index: 620

Text #16

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.0592. Min Act: -0.1700

Data Index: 3297235 (Open Web Text)

Max Activating Token Index: 803

Text #17

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.0597. Min Act: -0.1700

Data Index: 7502513 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.0681. Min Act: -0.1700

Data Index: 2675755 (Open Web Text)

Max Activating Token Index: 1016

Text #19

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.0492. Min Act: -0.1700

Data Index: 3987089 (Open Web Text)

Max Activating Token Index: 240