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

Dataset: Open Web Text

Neuron 351 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: 1.8256. Min Range: -1.8256

Max Act: 1.8256. Min Act: -0.1700

Data Index: 3054135 (Open Web Text)

Max Activating Token Index: 1020

Text #1

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.8234. Min Act: -0.1700

Data Index: 6237751 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.8027. Min Act: -0.1700

Data Index: 5381250 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.8080. Min Act: -0.1700

Data Index: 3895482 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7969. Min Act: -0.1700

Data Index: 6515691 (Open Web Text)

Max Activating Token Index: 1013

Text #5

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7773. Min Act: -0.1700

Data Index: 7059812 (Open Web Text)

Max Activating Token Index: 1019

Text #6

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7956. Min Act: -0.1700

Data Index: 2208227 (Open Web Text)

Max Activating Token Index: 1017

Text #7

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7999. Min Act: -0.1700

Data Index: 5537171 (Open Web Text)

Max Activating Token Index: 1020

Text #8

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7989. Min Act: -0.1700

Data Index: 6522710 (Open Web Text)

Max Activating Token Index: 1018

Text #9

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7856. Min Act: -0.1700

Data Index: 7059823 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7855. Min Act: -0.1700

Data Index: 520931 (Open Web Text)

Max Activating Token Index: 1017

Text #11

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7924. Min Act: -0.1700

Data Index: 6980548 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7790. Min Act: -0.1700

Data Index: 4946729 (Open Web Text)

Max Activating Token Index: 1018

Text #13

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7669. Min Act: -0.1700

Data Index: 5143643 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7829. Min Act: -0.1700

Data Index: 1310748 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7688. Min Act: -0.1700

Data Index: 2649595 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7677. Min Act: -0.1700

Data Index: 4945203 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7652. Min Act: -0.1700

Data Index: 7776757 (Open Web Text)

Max Activating Token Index: 1014

Text #18

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7579. Min Act: -0.1700

Data Index: 5143630 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.7605. Min Act: -0.1700

Data Index: 6233550 (Open Web Text)

Max Activating Token Index: 1022