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

Dataset: Open Web Text

Neuron 445 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: 3.4909. Min Range: -3.4909

Max Act: 3.4909. Min Act: -0.1700

Data Index: 1048794 (Open Web Text)

Max Activating Token Index: 1021

Text #1

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4822. Min Act: -0.1700

Data Index: 1061653 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4885. Min Act: -0.1700

Data Index: 4809729 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4883. Min Act: -0.1700

Data Index: 7556661 (Open Web Text)

Max Activating Token Index: 1017

Text #4

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4510. Min Act: -0.1700

Data Index: 4012631 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4607. Min Act: -0.1700

Data Index: 117808 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4558. Min Act: -0.1700

Data Index: 6808378 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4602. Min Act: -0.1700

Data Index: 5545678 (Open Web Text)

Max Activating Token Index: 1020

Text #8

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4547. Min Act: -0.1700

Data Index: 5495314 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4510. Min Act: -0.1700

Data Index: 5110000 (Open Web Text)

Max Activating Token Index: 1020

Text #10

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4506. Min Act: -0.1700

Data Index: 5056400 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4584. Min Act: -0.1700

Data Index: 4435647 (Open Web Text)

Max Activating Token Index: 1020

Text #12

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4560. Min Act: -0.1700

Data Index: 4151728 (Open Web Text)

Max Activating Token Index: 1020

Text #13

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4536. Min Act: -0.1700

Data Index: 3848485 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4589. Min Act: -0.1700

Data Index: 3690444 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4560. Min Act: -0.1700

Data Index: 3006441 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4618. Min Act: -0.1700

Data Index: 2824580 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4553. Min Act: -0.1700

Data Index: 2722346 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4650. Min Act: -0.1700

Data Index: 1007994 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4732. Min Act: -0.1700

Data Index: 739270 (Open Web Text)

Max Activating Token Index: 1020