Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1106 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.5847. Min Act: -0.1700
Data Index: 4668674 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.3972. Min Act: -0.1700
Data Index: 5674512 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.3972. Min Act: -0.1700
Data Index: 7043724 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.3660. Min Act: -0.1700
Data Index: 5482967 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.3972. Min Act: -0.1700
Data Index: 6872115 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.3660. Min Act: -0.1700
Data Index: 5537315 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.3035. Min Act: -0.1700
Data Index: 2832270 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.3035. Min Act: -0.1700
Data Index: 5721545 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.3035. Min Act: -0.1700
Data Index: 5235370 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.2722. Min Act: -0.1700
Data Index: 8348247 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.2410. Min Act: -0.1700
Data Index: 7219091 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.2722. Min Act: -0.1700
Data Index: 7550277 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.3035. Min Act: -0.1700
Data Index: 5381280 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.2722. Min Act: -0.1700
Data Index: 7907247 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.2410. Min Act: -0.1700
Data Index: 2692781 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.2097. Min Act: -0.1700
Data Index: 6020781 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.2097. Min Act: -0.1700
Data Index: 4371067 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.2097. Min Act: -0.1700
Data Index: 6917688 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.2097. Min Act: -0.1700
Data Index: 6937455 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5847. Min Range: -6.5847
Max Act: 6.1785. Min Act: -0.1700
Data Index: 5138389 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19