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

Dataset: Open Web Text

Neuron 1398 in Layer 3

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: 5.6064. Min Range: -5.6064

Max Act: 5.6064. Min Act: -0.1700

Data Index: 4299789 (Open Web Text)

Max Activating Token Index: 303

Text #1

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.4699. Min Act: -0.1700

Data Index: 2457797 (Open Web Text)

Max Activating Token Index: 641

Text #2

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.4619. Min Act: -0.1700

Data Index: 7225094 (Open Web Text)

Max Activating Token Index: 913

Text #3

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3780. Min Act: -0.1700

Data Index: 4523020 (Open Web Text)

Max Activating Token Index: 760

Text #4

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3875. Min Act: -0.1700

Data Index: 677596 (Open Web Text)

Max Activating Token Index: 118

Text #5

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3625. Min Act: -0.1700

Data Index: 6608836 (Open Web Text)

Max Activating Token Index: 275

Text #6

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3745. Min Act: -0.1700

Data Index: 8461965 (Open Web Text)

Max Activating Token Index: 687

Text #7

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3571. Min Act: -0.1700

Data Index: 5981461 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3638. Min Act: -0.1700

Data Index: 1719708 (Open Web Text)

Max Activating Token Index: 555

Text #9

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3224. Min Act: -0.1700

Data Index: 2469633 (Open Web Text)

Max Activating Token Index: 403

Text #10

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3504. Min Act: -0.1700

Data Index: 5956916 (Open Web Text)

Max Activating Token Index: 835

Text #11

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3222. Min Act: -0.1700

Data Index: 5029217 (Open Web Text)

Max Activating Token Index: 894

Text #12

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3144. Min Act: -0.1700

Data Index: 277352 (Open Web Text)

Max Activating Token Index: 242

Text #13

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3265. Min Act: -0.1700

Data Index: 2074894 (Open Web Text)

Max Activating Token Index: 996

Text #14

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3285. Min Act: -0.1700

Data Index: 6169652 (Open Web Text)

Max Activating Token Index: 775

Text #15

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.2859. Min Act: -0.1700

Data Index: 6404816 (Open Web Text)

Max Activating Token Index: 788

Text #16

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.2620. Min Act: -0.1700

Data Index: 6187876 (Open Web Text)

Max Activating Token Index: 959

Text #17

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.3074. Min Act: -0.1700

Data Index: 3919207 (Open Web Text)

Max Activating Token Index: 494

Text #18

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.2920. Min Act: -0.1700

Data Index: 3674826 (Open Web Text)

Max Activating Token Index: 822

Text #19

Max Range: 5.6064. Min Range: -5.6064

Max Act: 5.2961. Min Act: -0.1700

Data Index: 647356 (Open Web Text)

Max Activating Token Index: 591