Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4950 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.6045. Min Act: -0.1700
Data Index: 5880818 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.4483. Min Act: -0.1700
Data Index: 3162596 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.4170. Min Act: -0.1700
Data Index: 2649591 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.3858. Min Act: -0.1700
Data Index: 2147778 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.3233. Min Act: -0.1700
Data Index: 7663361 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.2920. Min Act: -0.1700
Data Index: 6241188 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.2295. Min Act: -0.1700
Data Index: 5536104 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.1670. Min Act: -0.1700
Data Index: 3151487 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.1670. Min Act: -0.1700
Data Index: 2205029 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.1670. Min Act: -0.1700
Data Index: 3469413 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.1358. Min Act: -0.1700
Data Index: 5585273 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.1045. Min Act: -0.1700
Data Index: 7354501 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.1045. Min Act: -0.1700
Data Index: 6804447 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.0420. Min Act: -0.1700
Data Index: 7380227 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.0733. Min Act: -0.1700
Data Index: 574747 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.0420. Min Act: -0.1700
Data Index: 5550505 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.0420. Min Act: -0.1700
Data Index: 3120825 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.0420. Min Act: -0.1700
Data Index: 2283679 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.0420. Min Act: -0.1700
Data Index: 3165167 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6045. Min Range: -5.6045
Max Act: 5.0420. Min Act: -0.1700
Data Index: 4936097 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19