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

Dataset: Open Web Text

Neuron 2120 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: 2.0588. Min Range: -2.0588

Max Act: 2.0588. Min Act: -0.1700

Data Index: 5865468 (Open Web Text)

Max Activating Token Index: 1020

Text #1

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.9594. Min Act: -0.1700

Data Index: 6710553 (Open Web Text)

Max Activating Token Index: 1016

Text #2

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.9427. Min Act: -0.1700

Data Index: 7360441 (Open Web Text)

Max Activating Token Index: 1014

Text #3

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.9249. Min Act: -0.1700

Data Index: 4373548 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.9235. Min Act: -0.1692

Data Index: 7875807 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8987. Min Act: -0.1700

Data Index: 653591 (Open Web Text)

Max Activating Token Index: 1017

Text #6

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.9046. Min Act: -0.1676

Data Index: 7875801 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8809. Min Act: -0.1700

Data Index: 7875811 (Open Web Text)

Max Activating Token Index: 1020

Text #8

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8871. Min Act: -0.1700

Data Index: 130322 (Open Web Text)

Max Activating Token Index: 1015

Text #9

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8928. Min Act: -0.1700

Data Index: 8494541 (Open Web Text)

Max Activating Token Index: 1005

Text #10

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8803. Min Act: -0.1700

Data Index: 6188772 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8873. Min Act: -0.1696

Data Index: 7633437 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8886. Min Act: -0.1700

Data Index: 7875799 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8844. Min Act: -0.1700

Data Index: 7633435 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8713. Min Act: -0.1658

Data Index: 7875808 (Open Web Text)

Max Activating Token Index: 1018

Text #15

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8677. Min Act: -0.1698

Data Index: 7875803 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8777. Min Act: -0.1700

Data Index: 1389871 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8746. Min Act: -0.1700

Data Index: 2899735 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8775. Min Act: -0.1700

Data Index: 6309794 (Open Web Text)

Max Activating Token Index: 990

Text #19

Max Range: 2.0588. Min Range: -2.0588

Max Act: 1.8554. Min Act: -0.1700

Data Index: 2778882 (Open Web Text)

Max Activating Token Index: 1021