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

Dataset: Open Web Text

Neuron 123 in Layer 4

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: 2.4397. Min Range: -2.4397

Max Act: 2.4397. Min Act: -0.1700

Data Index: 1844834 (Open Web Text)

Max Activating Token Index: 967

Text #1

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2583. Min Act: -0.1700

Data Index: 2802924 (Open Web Text)

Max Activating Token Index: 683

Text #2

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2641. Min Act: -0.1700

Data Index: 161229 (Open Web Text)

Max Activating Token Index: 282

Text #3

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2535. Min Act: -0.1700

Data Index: 5369184 (Open Web Text)

Max Activating Token Index: 558

Text #4

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2412. Min Act: -0.1700

Data Index: 4396659 (Open Web Text)

Max Activating Token Index: 404

Text #5

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.1945. Min Act: -0.1700

Data Index: 3510752 (Open Web Text)

Max Activating Token Index: 149

Text #6

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2023. Min Act: -0.1700

Data Index: 1973193 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2086. Min Act: -0.1700

Data Index: 8386576 (Open Web Text)

Max Activating Token Index: 175

Text #8

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.1872. Min Act: -0.1700

Data Index: 6392210 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2006. Min Act: -0.1700

Data Index: 4045526 (Open Web Text)

Max Activating Token Index: 552

Text #10

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2118. Min Act: -0.1700

Data Index: 4653494 (Open Web Text)

Max Activating Token Index: 519

Text #11

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2035. Min Act: -0.1700

Data Index: 2567694 (Open Web Text)

Max Activating Token Index: 711

Text #12

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2019. Min Act: -0.1700

Data Index: 6294343 (Open Web Text)

Max Activating Token Index: 1010

Text #13

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.1795. Min Act: -0.1700

Data Index: 3721892 (Open Web Text)

Max Activating Token Index: 206

Text #14

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.1772. Min Act: -0.1700

Data Index: 7673997 (Open Web Text)

Max Activating Token Index: 715

Text #15

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.1847. Min Act: -0.1700

Data Index: 108505 (Open Web Text)

Max Activating Token Index: 212

Text #16

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.2011. Min Act: -0.1700

Data Index: 5201010 (Open Web Text)

Max Activating Token Index: 567

Text #17

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.1751. Min Act: -0.1700

Data Index: 6070564 (Open Web Text)

Max Activating Token Index: 547

Text #18

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.1675. Min Act: -0.1700

Data Index: 4633227 (Open Web Text)

Max Activating Token Index: 935

Text #19

Max Range: 2.4397. Min Range: -2.4397

Max Act: 2.1754. Min Act: -0.1700

Data Index: 1997174 (Open Web Text)

Max Activating Token Index: 662