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

Dataset: Open Web Text

Neuron 2589 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: 3.0621. Min Range: -3.0621

Max Act: 3.0621. Min Act: -0.1700

Data Index: 3626992 (Open Web Text)

Max Activating Token Index: 293

Text #1

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.9018. Min Act: -0.1700

Data Index: 820160 (Open Web Text)

Max Activating Token Index: 212

Text #2

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8793. Min Act: -0.1700

Data Index: 4329648 (Open Web Text)

Max Activating Token Index: 192

Text #3

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8865. Min Act: -0.1700

Data Index: 5224208 (Open Web Text)

Max Activating Token Index: 185

Text #4

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8906. Min Act: -0.1700

Data Index: 7479812 (Open Web Text)

Max Activating Token Index: 378

Text #5

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8738. Min Act: -0.1700

Data Index: 5768614 (Open Web Text)

Max Activating Token Index: 178

Text #6

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8739. Min Act: -0.1700

Data Index: 4550193 (Open Web Text)

Max Activating Token Index: 188

Text #7

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8633. Min Act: -0.1700

Data Index: 4360783 (Open Web Text)

Max Activating Token Index: 223

Text #8

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8503. Min Act: -0.1700

Data Index: 4929896 (Open Web Text)

Max Activating Token Index: 118

Text #9

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8577. Min Act: -0.1700

Data Index: 2750729 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8515. Min Act: -0.1700

Data Index: 4387978 (Open Web Text)

Max Activating Token Index: 356

Text #11

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8505. Min Act: -0.1700

Data Index: 8203848 (Open Web Text)

Max Activating Token Index: 250

Text #12

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8304. Min Act: -0.1700

Data Index: 6311448 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8558. Min Act: -0.1700

Data Index: 4097967 (Open Web Text)

Max Activating Token Index: 362

Text #14

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8151. Min Act: -0.1700

Data Index: 6486090 (Open Web Text)

Max Activating Token Index: 127

Text #15

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8279. Min Act: -0.1700

Data Index: 6981937 (Open Web Text)

Max Activating Token Index: 172

Text #16

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8239. Min Act: -0.1700

Data Index: 4795037 (Open Web Text)

Max Activating Token Index: 151

Text #17

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8221. Min Act: -0.1700

Data Index: 6137932 (Open Web Text)

Max Activating Token Index: 235

Text #18

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8038. Min Act: -0.1700

Data Index: 6754145 (Open Web Text)

Max Activating Token Index: 307

Text #19

Max Range: 3.0621. Min Range: -3.0621

Max Act: 2.8071. Min Act: -0.1700

Data Index: 6067506 (Open Web Text)

Max Activating Token Index: 302