Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4894 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0956. Min Range: -7.0956
Max Act: 7.0956. Min Act: -0.1700
Data Index: 736378 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0956. Min Range: -7.0956
Max Act: 7.0644. Min Act: -0.1700
Data Index: 4990880 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0956. Min Range: -7.0956
Max Act: 7.0331. Min Act: -0.1700
Data Index: 4817677 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.9394. Min Act: -0.1700
Data Index: 1005097 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.8144. Min Act: -0.1700
Data Index: 4441695 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.7519. Min Act: -0.1700
Data Index: 5927718 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.7831. Min Act: -0.1700
Data Index: 1871201 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.6894. Min Act: -0.1700
Data Index: 1179085 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.6894. Min Act: -0.1700
Data Index: 7375998 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.6581. Min Act: -0.1700
Data Index: 8795916 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.6269. Min Act: -0.1700
Data Index: 6773565 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.6269. Min Act: -0.1700
Data Index: 1609460 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.6269. Min Act: -0.1700
Data Index: 1661989 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.6581. Min Act: -0.1700
Data Index: 3603351 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.6269. Min Act: -0.1700
Data Index: 6159867 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.6269. Min Act: -0.1700
Data Index: 2987650 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.6581. Min Act: -0.1700
Data Index: 2727540 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.5956. Min Act: -0.1700
Data Index: 456919 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.5956. Min Act: -0.1700
Data Index: 3450756 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0956. Min Range: -7.0956
Max Act: 6.5956. Min Act: -0.1700
Data Index: 2299127 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19