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

Dataset: Open Web Text

Neuron 240 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: 1.2167. Min Range: -1.2167

Max Act: 1.2167. Min Act: -0.1700

Data Index: 2854190 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.2013. Min Act: -0.1700

Data Index: 6649789 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1960. Min Act: -0.1700

Data Index: 6667030 (Open Web Text)

Max Activating Token Index: 1018

Text #3

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.2000. Min Act: -0.1700

Data Index: 42921 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1819. Min Act: -0.1700

Data Index: 8622406 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1722. Min Act: -0.1700

Data Index: 7632861 (Open Web Text)

Max Activating Token Index: 1020

Text #6

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1615. Min Act: -0.1700

Data Index: 8558172 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1627. Min Act: -0.1700

Data Index: 7632874 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1602. Min Act: -0.1700

Data Index: 717715 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1618. Min Act: -0.1700

Data Index: 42922 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1681. Min Act: -0.1700

Data Index: 4068712 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1573. Min Act: -0.1700

Data Index: 5158852 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1467. Min Act: -0.1700

Data Index: 7632866 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1438. Min Act: -0.1700

Data Index: 7632871 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1400. Min Act: -0.1700

Data Index: 2173415 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1330. Min Act: -0.1700

Data Index: 7632859 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1329. Min Act: -0.1700

Data Index: 3484367 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1238. Min Act: -0.1700

Data Index: 1744800 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1284. Min Act: -0.1700

Data Index: 4014027 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1358. Min Act: -0.1700

Data Index: 5567536 (Open Web Text)

Max Activating Token Index: 1013