Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2085. Min Range: -8.2085
Max Act: 8.2085. Min Act: -0.1700
Data Index: 2598915 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2085. Min Range: -8.2085
Max Act: 8.1460. Min Act: -0.1700
Data Index: 2225244 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2085. Min Range: -8.2085
Max Act: 8.0835. Min Act: -0.1700
Data Index: 4003373 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2085. Min Range: -8.2085
Max Act: 8.0210. Min Act: -0.1700
Data Index: 7545459 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2085. Min Range: -8.2085
Max Act: 8.0210. Min Act: -0.1700
Data Index: 7845695 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2085. Min Range: -8.2085
Max Act: 8.0210. Min Act: -0.1700
Data Index: 2060634 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2085. Min Range: -8.2085
Max Act: 8.0835. Min Act: -0.1700
Data Index: 6367857 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.9585. Min Act: -0.1700
Data Index: 7328286 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.8960. Min Act: -0.1700
Data Index: 3623108 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.9585. Min Act: -0.1700
Data Index: 7877471 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.9585. Min Act: -0.1700
Data Index: 1551808 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.8960. Min Act: -0.1700
Data Index: 2722392 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.8960. Min Act: -0.1700
Data Index: 7923909 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.8960. Min Act: -0.1700
Data Index: 3984072 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.8960. Min Act: -0.1700
Data Index: 2277629 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.8960. Min Act: -0.1700
Data Index: 6577877 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.8960. Min Act: -0.1700
Data Index: 6397520 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.8960. Min Act: -0.1700
Data Index: 2523988 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.8335. Min Act: -0.1700
Data Index: 7353111 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2085. Min Range: -8.2085
Max Act: 7.8335. Min Act: -0.1700
Data Index: 5459084 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19