Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2546 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.6956. Min Act: -0.1700
Data Index: 7148735 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.6956. Min Act: -0.1700
Data Index: 7404513 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.6956. Min Act: -0.1700
Data Index: 1592868 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.6331. Min Act: -0.1700
Data Index: 6783238 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.6643. Min Act: -0.1700
Data Index: 6265013 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.6643. Min Act: -0.1700
Data Index: 5137707 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.6331. Min Act: -0.1700
Data Index: 5156762 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.6018. Min Act: -0.1700
Data Index: 816491 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.5706. Min Act: -0.1700
Data Index: 4228307 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.5393. Min Act: -0.1700
Data Index: 3895974 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.5081. Min Act: -0.1700
Data Index: 1496046 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.5081. Min Act: -0.1700
Data Index: 1093231 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.4456. Min Act: -0.1700
Data Index: 4356934 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.4768. Min Act: -0.1700
Data Index: 2900 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.5081. Min Act: -0.1700
Data Index: 4491753 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.4768. Min Act: -0.1700
Data Index: 7337952 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.4768. Min Act: -0.1700
Data Index: 7164196 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.4456. Min Act: -0.1700
Data Index: 4799012 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.4456. Min Act: -0.1700
Data Index: 3084151 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6956. Min Range: -5.6956
Max Act: 5.4456. Min Act: -0.1700
Data Index: 8648802 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19