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

Dataset: Open Web Text

Neuron 2853 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: 1.8887. Min Range: -1.8887

Max Act: 1.8887. Min Act: -0.1700

Data Index: 7637748 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.8311. Min Act: -0.1700

Data Index: 6077985 (Open Web Text)

Max Activating Token Index: 1018

Text #2

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.8113. Min Act: -0.1700

Data Index: 7512879 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7781. Min Act: -0.1700

Data Index: 6045857 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7329. Min Act: -0.1700

Data Index: 5153600 (Open Web Text)

Max Activating Token Index: 995

Text #5

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7492. Min Act: -0.1700

Data Index: 6078307 (Open Web Text)

Max Activating Token Index: 1016

Text #6

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7298. Min Act: -0.1700

Data Index: 8371770 (Open Web Text)

Max Activating Token Index: 1009

Text #7

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7455. Min Act: -0.1700

Data Index: 2023040 (Open Web Text)

Max Activating Token Index: 1016

Text #8

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7560. Min Act: -0.1700

Data Index: 7364595 (Open Web Text)

Max Activating Token Index: 998

Text #9

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7327. Min Act: -0.1700

Data Index: 1623704 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7238. Min Act: -0.1700

Data Index: 3327222 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7037. Min Act: -0.1700

Data Index: 4228635 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7593. Min Act: -0.1700

Data Index: 5596574 (Open Web Text)

Max Activating Token Index: 1018

Text #13

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6759. Min Act: -0.1700

Data Index: 6150223 (Open Web Text)

Max Activating Token Index: 1009

Text #14

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6807. Min Act: -0.1700

Data Index: 4882357 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.7473. Min Act: -0.1700

Data Index: 8567632 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6870. Min Act: -0.1700

Data Index: 5617265 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6889. Min Act: -0.1700

Data Index: 7689043 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6834. Min Act: -0.1700

Data Index: 1457006 (Open Web Text)

Max Activating Token Index: 986

Text #19

Max Range: 1.8887. Min Range: -1.8887

Max Act: 1.6861. Min Act: -0.1700

Data Index: 1839081 (Open Web Text)

Max Activating Token Index: 1020