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

Dataset: Open Web Text

Neuron 2914 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: 0.8048. Min Range: -0.8048

Max Act: 0.8048. Min Act: -0.1700

Data Index: 6203934 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.7776. Min Act: -0.1700

Data Index: 4697424 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.7724. Min Act: -0.1700

Data Index: 5180471 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.7545. Min Act: -0.1700

Data Index: 8332572 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.7590. Min Act: -0.1700

Data Index: 4836725 (Open Web Text)

Max Activating Token Index: 974

Text #5

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.7413. Min Act: -0.1699

Data Index: 5040417 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.7132. Min Act: -0.1700

Data Index: 1576569 (Open Web Text)

Max Activating Token Index: 995

Text #7

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.7131. Min Act: -0.1700

Data Index: 2626864 (Open Web Text)

Max Activating Token Index: 1020

Text #8

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6965. Min Act: -0.1700

Data Index: 2776008 (Open Web Text)

Max Activating Token Index: 970

Text #9

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6859. Min Act: -0.1700

Data Index: 2542840 (Open Web Text)

Max Activating Token Index: 1006

Text #10

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6901. Min Act: -0.1700

Data Index: 5953784 (Open Web Text)

Max Activating Token Index: 994

Text #11

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6866. Min Act: -0.1700

Data Index: 610068 (Open Web Text)

Max Activating Token Index: 1014

Text #12

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6891. Min Act: -0.1700

Data Index: 3218402 (Open Web Text)

Max Activating Token Index: 1016

Text #13

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6940. Min Act: -0.1700

Data Index: 368501 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6802. Min Act: -0.1700

Data Index: 3377018 (Open Web Text)

Max Activating Token Index: 949

Text #15

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6726. Min Act: -0.1700

Data Index: 1300326 (Open Web Text)

Max Activating Token Index: 1009

Text #16

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6687. Min Act: -0.1700

Data Index: 4874011 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6652. Min Act: -0.1700

Data Index: 3227860 (Open Web Text)

Max Activating Token Index: 1019

Text #18

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6798. Min Act: -0.1700

Data Index: 1143599 (Open Web Text)

Max Activating Token Index: 1017

Text #19

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.6720. Min Act: -0.1700

Data Index: 4214362 (Open Web Text)

Max Activating Token Index: 1013