Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4802 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.3903. Min Act: -0.1700
Data Index: 6751105 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.3903. Min Act: -0.1700
Data Index: 2447982 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.3278. Min Act: -0.1700
Data Index: 1349936 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.2653. Min Act: -0.1700
Data Index: 7990047 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.2340. Min Act: -0.1700
Data Index: 7537024 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.2340. Min Act: -0.1700
Data Index: 5345549 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.2340. Min Act: -0.1700
Data Index: 202981 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.2340. Min Act: -0.1700
Data Index: 2534032 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.2340. Min Act: -0.1700
Data Index: 5316747 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.2028. Min Act: -0.1700
Data Index: 3775965 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.2028. Min Act: -0.1700
Data Index: 6974696 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.2028. Min Act: -0.1700
Data Index: 634874 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.2028. Min Act: -0.1700
Data Index: 3321911 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.1715. Min Act: -0.1700
Data Index: 6154477 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.1403. Min Act: -0.1700
Data Index: 490088 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.1090. Min Act: -0.1700
Data Index: 7229389 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.1090. Min Act: -0.1700
Data Index: 1954487 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.0778. Min Act: -0.1700
Data Index: 1158514 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.0778. Min Act: -0.1700
Data Index: 3259966 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3903. Min Range: -7.3903
Max Act: 7.0778. Min Act: -0.1700
Data Index: 1834456 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19