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

Dataset: Open Web Text

Neuron 2938 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: 4.5252. Min Range: -4.5252

Max Act: 4.5252. Min Act: -0.1700

Data Index: 3171635 (Open Web Text)

Max Activating Token Index: 782

Text #1

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.4682. Min Act: -0.1700

Data Index: 7309327 (Open Web Text)

Max Activating Token Index: 408

Text #2

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.4656. Min Act: -0.1700

Data Index: 8165405 (Open Web Text)

Max Activating Token Index: 797

Text #3

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.4218. Min Act: -0.1700

Data Index: 4264799 (Open Web Text)

Max Activating Token Index: 161

Text #4

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3984. Min Act: -0.1700

Data Index: 5986468 (Open Web Text)

Max Activating Token Index: 232

Text #5

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.4022. Min Act: -0.1700

Data Index: 7369223 (Open Web Text)

Max Activating Token Index: 525

Text #6

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3987. Min Act: -0.1700

Data Index: 812923 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3989. Min Act: -0.1700

Data Index: 2483939 (Open Web Text)

Max Activating Token Index: 829

Text #8

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3815. Min Act: -0.1700

Data Index: 2303528 (Open Web Text)

Max Activating Token Index: 707

Text #9

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3531. Min Act: -0.1700

Data Index: 2874108 (Open Web Text)

Max Activating Token Index: 987

Text #10

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3358. Min Act: -0.1700

Data Index: 8822244 (Open Web Text)

Max Activating Token Index: 591

Text #11

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3365. Min Act: -0.1700

Data Index: 3547562 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3501. Min Act: -0.1700

Data Index: 3270084 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3668. Min Act: -0.1700

Data Index: 3107704 (Open Web Text)

Max Activating Token Index: 93

Text #14

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3308. Min Act: -0.1700

Data Index: 8020413 (Open Web Text)

Max Activating Token Index: 247

Text #15

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.2836. Min Act: -0.1700

Data Index: 3391766 (Open Web Text)

Max Activating Token Index: 799

Text #16

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3265. Min Act: -0.1700

Data Index: 8223528 (Open Web Text)

Max Activating Token Index: 384

Text #17

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3333. Min Act: -0.1700

Data Index: 1226948 (Open Web Text)

Max Activating Token Index: 137

Text #18

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3024. Min Act: -0.1700

Data Index: 7811367 (Open Web Text)

Max Activating Token Index: 801

Text #19

Max Range: 4.5252. Min Range: -4.5252

Max Act: 4.3210. Min Act: -0.1700

Data Index: 5384054 (Open Web Text)

Max Activating Token Index: 810