Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1200 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.2144. Min Act: -0.1700
Data Index: 5374971 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0894. Min Act: -0.1700
Data Index: 218452 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0581. Min Act: -0.1700
Data Index: 7046576 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0581. Min Act: -0.1700
Data Index: 4697694 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9644. Min Act: -0.1700
Data Index: 6560194 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9644. Min Act: -0.1700
Data Index: 8685847 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9644. Min Act: -0.1700
Data Index: 4202278 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9331. Min Act: -0.1700
Data Index: 4578922 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9331. Min Act: -0.1700
Data Index: 6151686 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8706. Min Act: -0.1700
Data Index: 6157814 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8706. Min Act: -0.1700
Data Index: 2236183 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 2339138 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 3538985 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 6473732 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8081. Min Act: -0.1700
Data Index: 3912970 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7769. Min Act: -0.1700
Data Index: 4786742 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7769. Min Act: -0.1700
Data Index: 4520283 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7769. Min Act: -0.1700
Data Index: 8799012 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7769. Min Act: -0.1700
Data Index: 4711115 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7456. Min Act: -0.1700
Data Index: 4562660 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19