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

Dataset: Open Web Text

Neuron 191 in Layer 2

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: 6.5737. Min Range: -6.5737

Max Act: 6.5369. Min Act: -0.1700

Data Index: 7229089 (Open Web Text)

Max Activating Token Index: 710

Text #1

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.5409. Min Act: -0.1700

Data Index: 5090081 (Open Web Text)

Max Activating Token Index: 911

Text #2

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.5143. Min Act: -0.1700

Data Index: 157775 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.5737. Min Act: -0.1700

Data Index: 1161107 (Open Web Text)

Max Activating Token Index: 343

Text #4

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4901. Min Act: -0.1700

Data Index: 3146659 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4360. Min Act: -0.1700

Data Index: 6135621 (Open Web Text)

Max Activating Token Index: 153

Text #6

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4146. Min Act: -0.1700

Data Index: 3828773 (Open Web Text)

Max Activating Token Index: 748

Text #7

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4419. Min Act: -0.1700

Data Index: 7840460 (Open Web Text)

Max Activating Token Index: 454

Text #8

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4414. Min Act: -0.1700

Data Index: 6884686 (Open Web Text)

Max Activating Token Index: 943

Text #9

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4586. Min Act: -0.1698

Data Index: 3819364 (Open Web Text)

Max Activating Token Index: 788

Text #10

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4487. Min Act: -0.1700

Data Index: 7320080 (Open Web Text)

Max Activating Token Index: 164

Text #11

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4446. Min Act: -0.1700

Data Index: 6814862 (Open Web Text)

Max Activating Token Index: 311

Text #12

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4278. Min Act: -0.1700

Data Index: 5860957 (Open Web Text)

Max Activating Token Index: 515

Text #13

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4216. Min Act: -0.1700

Data Index: 8640573 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.3853. Min Act: -0.1700

Data Index: 5089732 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4471. Min Act: -0.1700

Data Index: 1087762 (Open Web Text)

Max Activating Token Index: 784

Text #16

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.3789. Min Act: -0.1700

Data Index: 5544437 (Open Web Text)

Max Activating Token Index: 262

Text #17

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.3926. Min Act: -0.1700

Data Index: 4005192 (Open Web Text)

Max Activating Token Index: 373

Text #18

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.4116. Min Act: -0.1700

Data Index: 5269241 (Open Web Text)

Max Activating Token Index: 63

Text #19

Max Range: 6.5737. Min Range: -6.5737

Max Act: 6.3680. Min Act: -0.1700

Data Index: 1853762 (Open Web Text)

Max Activating Token Index: 130