Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1526 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4430. Min Range: -6.4430
Max Act: 6.4430. Min Act: -0.1700
Data Index: 624245 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4430. Min Range: -6.4430
Max Act: 6.2555. Min Act: -0.1700
Data Index: 668777 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4430. Min Range: -6.4430
Max Act: 6.2243. Min Act: -0.1700
Data Index: 2411987 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4430. Min Range: -6.4430
Max Act: 6.1618. Min Act: -0.1700
Data Index: 5403706 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4430. Min Range: -6.4430
Max Act: 6.1618. Min Act: -0.1700
Data Index: 4149496 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4430. Min Range: -6.4430
Max Act: 6.1930. Min Act: -0.1700
Data Index: 6119014 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4430. Min Range: -6.4430
Max Act: 6.1305. Min Act: -0.1700
Data Index: 2373080 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4430. Min Range: -6.4430
Max Act: 6.0368. Min Act: -0.1700
Data Index: 3542283 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4430. Min Range: -6.4430
Max Act: 6.0055. Min Act: -0.1700
Data Index: 7850005 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4430. Min Range: -6.4430
Max Act: 6.0055. Min Act: -0.1700
Data Index: 829108 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4430. Min Range: -6.4430
Max Act: 5.9430. Min Act: -0.1700
Data Index: 8228318 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4430. Min Range: -6.4430
Max Act: 5.9430. Min Act: -0.1700
Data Index: 3923780 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4430. Min Range: -6.4430
Max Act: 5.9118. Min Act: -0.1700
Data Index: 6715730 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4430. Min Range: -6.4430
Max Act: 5.9430. Min Act: -0.1700
Data Index: 3483142 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4430. Min Range: -6.4430
Max Act: 5.9430. Min Act: -0.1700
Data Index: 650775 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4430. Min Range: -6.4430
Max Act: 5.9118. Min Act: -0.1700
Data Index: 6156190 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4430. Min Range: -6.4430
Max Act: 5.9118. Min Act: -0.1700
Data Index: 7226787 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4430. Min Range: -6.4430
Max Act: 5.9118. Min Act: -0.1700
Data Index: 7054765 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4430. Min Range: -6.4430
Max Act: 5.9118. Min Act: -0.1700
Data Index: 4292583 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4430. Min Range: -6.4430
Max Act: 5.9118. Min Act: -0.1700
Data Index: 2062880 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19