Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0593. Min Range: -5.0593
Max Act: 5.0593. Min Act: -0.1700
Data Index: 2085640 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0593. Min Range: -5.0593
Max Act: 5.0593. Min Act: -0.1700
Data Index: 7006927 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.9343. Min Act: -0.1700
Data Index: 4560971 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.7781. Min Act: -0.1700
Data Index: 7006930 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6843. Min Act: -0.1700
Data Index: 463828 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6531. Min Act: -0.1700
Data Index: 8608166 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6218. Min Act: -0.1700
Data Index: 5195983 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6218. Min Act: -0.1700
Data Index: 7272245 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6531. Min Act: -0.1700
Data Index: 7719133 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6218. Min Act: -0.1700
Data Index: 6993966 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6531. Min Act: -0.1700
Data Index: 5937817 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6218. Min Act: -0.1700
Data Index: 1102181 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6218. Min Act: -0.1700
Data Index: 8613318 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6218. Min Act: -0.1700
Data Index: 7037202 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6218. Min Act: -0.1700
Data Index: 5279863 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.6218. Min Act: -0.1700
Data Index: 5787021 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.5906. Min Act: -0.1700
Data Index: 6269034 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.5906. Min Act: -0.1700
Data Index: 822615 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.5906. Min Act: -0.1700
Data Index: 4471750 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0593. Min Range: -5.0593
Max Act: 4.5593. Min Act: -0.1700
Data Index: 1961904 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19