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

Dataset: Open Web Text

Neuron 735 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: 1.8747. Min Range: -1.8747

Max Act: 1.8747. Min Act: -0.1697

Data Index: 4242949 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8089. Min Act: -0.1700

Data Index: 2679995 (Open Web Text)

Max Activating Token Index: 916

Text #2

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8134. Min Act: -0.1700

Data Index: 4442433 (Open Web Text)

Max Activating Token Index: 122

Text #3

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8000. Min Act: -0.1692

Data Index: 4751448 (Open Web Text)

Max Activating Token Index: 926

Text #4

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7936. Min Act: -0.1698

Data Index: 631417 (Open Web Text)

Max Activating Token Index: 1017

Text #5

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7779. Min Act: -0.1700

Data Index: 7080012 (Open Web Text)

Max Activating Token Index: 189

Text #6

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7735. Min Act: -0.1700

Data Index: 4632214 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7772. Min Act: -0.1700

Data Index: 8494437 (Open Web Text)

Max Activating Token Index: 719

Text #8

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7619. Min Act: -0.1700

Data Index: 3294585 (Open Web Text)

Max Activating Token Index: 698

Text #9

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7552. Min Act: -0.1700

Data Index: 524876 (Open Web Text)

Max Activating Token Index: 324

Text #10

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7361. Min Act: -0.1700

Data Index: 5713145 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7377. Min Act: -0.1699

Data Index: 4889041 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7415. Min Act: -0.1700

Data Index: 8643884 (Open Web Text)

Max Activating Token Index: 703

Text #13

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7279. Min Act: -0.1700

Data Index: 394269 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7289. Min Act: -0.1700

Data Index: 4288141 (Open Web Text)

Max Activating Token Index: 919

Text #15

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7229. Min Act: -0.1700

Data Index: 7654673 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7213. Min Act: -0.1700

Data Index: 1573914 (Open Web Text)

Max Activating Token Index: 416

Text #17

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7218. Min Act: -0.1700

Data Index: 2680002 (Open Web Text)

Max Activating Token Index: 214

Text #18

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7286. Min Act: -0.1700

Data Index: 5290488 (Open Web Text)

Max Activating Token Index: 342

Text #19

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7229. Min Act: -0.1700

Data Index: 760210 (Open Web Text)

Max Activating Token Index: 215