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

Dataset: Open Web Text

Neuron 1919 in Layer 0

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: 3.0097. Min Range: -3.0097

Max Act: 3.0097. Min Act: -0.1700

Data Index: 7839024 (Open Web Text)

Max Activating Token Index: 80

Text #1

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9944. Min Act: -0.1700

Data Index: 3028576 (Open Web Text)

Max Activating Token Index: 138

Text #2

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9927. Min Act: -0.1700

Data Index: 39087 (Open Web Text)

Max Activating Token Index: 105

Text #3

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9828. Min Act: -0.1700

Data Index: 2018010 (Open Web Text)

Max Activating Token Index: 29

Text #4

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9727. Min Act: -0.1700

Data Index: 8718081 (Open Web Text)

Max Activating Token Index: 1019

Text #5

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9859. Min Act: -0.1700

Data Index: 719491 (Open Web Text)

Max Activating Token Index: 25

Text #6

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9752. Min Act: -0.1700

Data Index: 1674652 (Open Web Text)

Max Activating Token Index: 613

Text #7

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9728. Min Act: -0.1700

Data Index: 2117320 (Open Web Text)

Max Activating Token Index: 656

Text #8

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9667. Min Act: -0.1700

Data Index: 3317837 (Open Web Text)

Max Activating Token Index: 818

Text #9

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9545. Min Act: -0.1700

Data Index: 2601873 (Open Web Text)

Max Activating Token Index: 513

Text #10

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9498. Min Act: -0.1700

Data Index: 6236972 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9464. Min Act: -0.1700

Data Index: 1561669 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9490. Min Act: -0.1700

Data Index: 2033331 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9387. Min Act: -0.1700

Data Index: 1440451 (Open Web Text)

Max Activating Token Index: 521

Text #14

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9454. Min Act: -0.1700

Data Index: 6838159 (Open Web Text)

Max Activating Token Index: 832

Text #15

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9500. Min Act: -0.1700

Data Index: 6577703 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9260. Min Act: -0.1700

Data Index: 4111373 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9264. Min Act: -0.1700

Data Index: 3890605 (Open Web Text)

Max Activating Token Index: 494

Text #18

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9294. Min Act: -0.1700

Data Index: 8033919 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9249. Min Act: -0.1700

Data Index: 4975563 (Open Web Text)

Max Activating Token Index: 43