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

Dataset: Open Web Text

Neuron 1602 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: 0.8825. Min Range: -0.8825

Max Act: 0.8825. Min Act: -0.1700

Data Index: 2074407 (Open Web Text)

Max Activating Token Index: 1012

Text #1

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7941. Min Act: -0.1700

Data Index: 4561869 (Open Web Text)

Max Activating Token Index: 1016

Text #2

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7858. Min Act: -0.1700

Data Index: 1582427 (Open Web Text)

Max Activating Token Index: 1004

Text #3

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7730. Min Act: -0.1700

Data Index: 4515191 (Open Web Text)

Max Activating Token Index: 1019

Text #4

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7855. Min Act: -0.1700

Data Index: 3958931 (Open Web Text)

Max Activating Token Index: 1014

Text #5

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7804. Min Act: -0.1700

Data Index: 8354145 (Open Web Text)

Max Activating Token Index: 1012

Text #6

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7633. Min Act: -0.1700

Data Index: 415001 (Open Web Text)

Max Activating Token Index: 1020

Text #7

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7635. Min Act: -0.1700

Data Index: 7996155 (Open Web Text)

Max Activating Token Index: 1002

Text #8

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7680. Min Act: -0.1700

Data Index: 7368651 (Open Web Text)

Max Activating Token Index: 1005

Text #9

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7749. Min Act: -0.1700

Data Index: 7596230 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7808. Min Act: -0.1700

Data Index: 7198317 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7677. Min Act: -0.1700

Data Index: 1626669 (Open Web Text)

Max Activating Token Index: 1000

Text #12

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7686. Min Act: -0.1700

Data Index: 8648348 (Open Web Text)

Max Activating Token Index: 997

Text #13

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7683. Min Act: -0.1700

Data Index: 6893668 (Open Web Text)

Max Activating Token Index: 1013

Text #14

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7657. Min Act: -0.1700

Data Index: 27385 (Open Web Text)

Max Activating Token Index: 997

Text #15

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7676. Min Act: -0.1700

Data Index: 2137429 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7680. Min Act: -0.1700

Data Index: 8066296 (Open Web Text)

Max Activating Token Index: 1007

Text #17

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7644. Min Act: -0.1700

Data Index: 2596225 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7667. Min Act: -0.1700

Data Index: 7249648 (Open Web Text)

Max Activating Token Index: 1005

Text #19

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7698. Min Act: -0.1700

Data Index: 8225095 (Open Web Text)

Max Activating Token Index: 983