Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5578 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.4581. Min Act: -0.1700
Data Index: 973099 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.3331. Min Act: -0.1700
Data Index: 5389812 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.2081. Min Act: -0.1700
Data Index: 4667999 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.1769. Min Act: -0.1700
Data Index: 2664155 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.2394. Min Act: -0.1700
Data Index: 4027914 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.1144. Min Act: -0.1700
Data Index: 948541 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.0831. Min Act: -0.1700
Data Index: 5837543 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.0831. Min Act: -0.1700
Data Index: 6292893 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.0831. Min Act: -0.1700
Data Index: 952950 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.0831. Min Act: -0.1700
Data Index: 7078557 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4581. Min Range: -7.4581
Max Act: 7.0519. Min Act: -0.1700
Data Index: 286485 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4581. Min Range: -7.4581
Max Act: 6.9894. Min Act: -0.1700
Data Index: 8552115 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4581. Min Range: -7.4581
Max Act: 6.9581. Min Act: -0.1700
Data Index: 6642533 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4581. Min Range: -7.4581
Max Act: 6.9269. Min Act: -0.1700
Data Index: 8051118 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4581. Min Range: -7.4581
Max Act: 6.9269. Min Act: -0.1700
Data Index: 2605282 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4581. Min Range: -7.4581
Max Act: 6.9269. Min Act: -0.1700
Data Index: 1715895 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4581. Min Range: -7.4581
Max Act: 6.8644. Min Act: -0.1700
Data Index: 1866266 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4581. Min Range: -7.4581
Max Act: 6.8644. Min Act: -0.1700
Data Index: 2819935 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4581. Min Range: -7.4581
Max Act: 6.8644. Min Act: -0.1700
Data Index: 921560 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4581. Min Range: -7.4581
Max Act: 6.8644. Min Act: -0.1700
Data Index: 4917900 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19