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

Dataset: Open Web Text

Neuron 146 in Layer 1

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: 1.4380. Min Range: -1.4380

Max Act: 1.4380. Min Act: -0.1700

Data Index: 6667030 (Open Web Text)

Max Activating Token Index: 1018

Text #1

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.1340. Min Act: -0.1700

Data Index: 5704559 (Open Web Text)

Max Activating Token Index: 1009

Text #2

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.1275. Min Act: -0.1700

Data Index: 4865074 (Open Web Text)

Max Activating Token Index: 1010

Text #3

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.1320. Min Act: -0.1700

Data Index: 2491727 (Open Web Text)

Max Activating Token Index: 1012

Text #4

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.1165. Min Act: -0.1700

Data Index: 5103605 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.1017. Min Act: -0.1700

Data Index: 3393659 (Open Web Text)

Max Activating Token Index: 1013

Text #6

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.1116. Min Act: -0.1700

Data Index: 4173741 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0999. Min Act: -0.1700

Data Index: 3393662 (Open Web Text)

Max Activating Token Index: 1014

Text #8

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0995. Min Act: -0.1700

Data Index: 8252132 (Open Web Text)

Max Activating Token Index: 1013

Text #9

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0820. Min Act: -0.1700

Data Index: 2170544 (Open Web Text)

Max Activating Token Index: 1021

Text #10

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0906. Min Act: -0.1700

Data Index: 1692942 (Open Web Text)

Max Activating Token Index: 1013

Text #11

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0872. Min Act: -0.1700

Data Index: 1887361 (Open Web Text)

Max Activating Token Index: 1017

Text #12

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0673. Min Act: -0.1700

Data Index: 3919745 (Open Web Text)

Max Activating Token Index: 1005

Text #13

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0768. Min Act: -0.1700

Data Index: 843640 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0719. Min Act: -0.1700

Data Index: 4584217 (Open Web Text)

Max Activating Token Index: 1011

Text #15

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0641. Min Act: -0.1700

Data Index: 491762 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0863. Min Act: -0.1700

Data Index: 3393658 (Open Web Text)

Max Activating Token Index: 1015

Text #17

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0688. Min Act: -0.1700

Data Index: 2636535 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0613. Min Act: -0.1700

Data Index: 3662936 (Open Web Text)

Max Activating Token Index: 1017

Text #19

Max Range: 1.4380. Min Range: -1.4380

Max Act: 1.0673. Min Act: -0.1700

Data Index: 5440302 (Open Web Text)

Max Activating Token Index: 1011