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

Dataset: Open Web Text

Neuron 335 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: 1.6721. Min Range: -1.6721

Max Act: 1.6721. Min Act: -0.1700

Data Index: 7979297 (Open Web Text)

Max Activating Token Index: 256

Text #1

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6596. Min Act: -0.1700

Data Index: 4986425 (Open Web Text)

Max Activating Token Index: 309

Text #2

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6526. Min Act: -0.1700

Data Index: 7979296 (Open Web Text)

Max Activating Token Index: 552

Text #3

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6368. Min Act: -0.1700

Data Index: 3551230 (Open Web Text)

Max Activating Token Index: 409

Text #4

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6322. Min Act: -0.1699

Data Index: 3050719 (Open Web Text)

Max Activating Token Index: 821

Text #5

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6215. Min Act: -0.1700

Data Index: 4096570 (Open Web Text)

Max Activating Token Index: 407

Text #6

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6240. Min Act: -0.1700

Data Index: 2039123 (Open Web Text)

Max Activating Token Index: 151

Text #7

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6307. Min Act: -0.1700

Data Index: 7681453 (Open Web Text)

Max Activating Token Index: 523

Text #8

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6248. Min Act: -0.1700

Data Index: 3719670 (Open Web Text)

Max Activating Token Index: 567

Text #9

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6061. Min Act: -0.1700

Data Index: 1232199 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6075. Min Act: -0.1700

Data Index: 7513890 (Open Web Text)

Max Activating Token Index: 295

Text #11

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6072. Min Act: -0.1700

Data Index: 7979298 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6118. Min Act: -0.1700

Data Index: 2418495 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6096. Min Act: -0.1700

Data Index: 8039012 (Open Web Text)

Max Activating Token Index: 207

Text #14

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6030. Min Act: -0.1700

Data Index: 4577664 (Open Web Text)

Max Activating Token Index: 326

Text #15

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.5958. Min Act: -0.1699

Data Index: 4255115 (Open Web Text)

Max Activating Token Index: 397

Text #16

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6015. Min Act: -0.1700

Data Index: 654162 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.5998. Min Act: -0.1700

Data Index: 5680522 (Open Web Text)

Max Activating Token Index: 644

Text #18

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6000. Min Act: -0.1700

Data Index: 6584176 (Open Web Text)

Max Activating Token Index: 907

Text #19

Max Range: 1.6721. Min Range: -1.6721

Max Act: 1.6016. Min Act: -0.1700

Data Index: 586666 (Open Web Text)

Max Activating Token Index: 191