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

Dataset: Open Web Text

Neuron 704 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: 5.3086. Min Range: -5.3086

Max Act: 5.2760. Min Act: -0.1700

Data Index: 5181639 (Open Web Text)

Max Activating Token Index: 383

Text #1

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.2960. Min Act: -0.1700

Data Index: 1144903 (Open Web Text)

Max Activating Token Index: 605

Text #2

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.2130. Min Act: -0.1700

Data Index: 6881404 (Open Web Text)

Max Activating Token Index: 525

Text #3

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.2574. Min Act: -0.1700

Data Index: 8062319 (Open Web Text)

Max Activating Token Index: 442

Text #4

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.3086. Min Act: -0.1700

Data Index: 8198559 (Open Web Text)

Max Activating Token Index: 460

Text #5

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.1994. Min Act: -0.1700

Data Index: 8510701 (Open Web Text)

Max Activating Token Index: 981

Text #6

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.1538. Min Act: -0.1700

Data Index: 5679062 (Open Web Text)

Max Activating Token Index: 468

Text #7

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.1239. Min Act: -0.1700

Data Index: 8534712 (Open Web Text)

Max Activating Token Index: 204

Text #8

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.1564. Min Act: -0.1700

Data Index: 2843579 (Open Web Text)

Max Activating Token Index: 262

Text #9

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.1339. Min Act: -0.1700

Data Index: 1707500 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.1134. Min Act: -0.1700

Data Index: 5264796 (Open Web Text)

Max Activating Token Index: 987

Text #11

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.1382. Min Act: -0.1700

Data Index: 441136 (Open Web Text)

Max Activating Token Index: 971

Text #12

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.1186. Min Act: -0.1700

Data Index: 2055815 (Open Web Text)

Max Activating Token Index: 513

Text #13

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.0892. Min Act: -0.1700

Data Index: 5611846 (Open Web Text)

Max Activating Token Index: 772

Text #14

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.0973. Min Act: -0.1700

Data Index: 850081 (Open Web Text)

Max Activating Token Index: 764

Text #15

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.0714. Min Act: -0.1700

Data Index: 6134815 (Open Web Text)

Max Activating Token Index: 218

Text #16

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.0993. Min Act: -0.1700

Data Index: 8632169 (Open Web Text)

Max Activating Token Index: 997

Text #17

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.0551. Min Act: -0.1700

Data Index: 5542928 (Open Web Text)

Max Activating Token Index: 272

Text #18

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.0564. Min Act: -0.1700

Data Index: 2589864 (Open Web Text)

Max Activating Token Index: 125

Text #19

Max Range: 5.3086. Min Range: -5.3086

Max Act: 5.0497. Min Act: -0.1700

Data Index: 5121305 (Open Web Text)

Max Activating Token Index: 157