Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1865 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2593. Min Range: -7.2593
Max Act: 7.2593. Min Act: -0.1700
Data Index: 6049100 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.8531. Min Act: -0.1700
Data Index: 7603609 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.8218. Min Act: -0.1700
Data Index: 5780576 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.7906. Min Act: -0.1700
Data Index: 6118891 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.7281. Min Act: -0.1700
Data Index: 5066978 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.5718. Min Act: -0.1700
Data Index: 4640303 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.5406. Min Act: -0.1700
Data Index: 4239347 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.5093. Min Act: -0.1700
Data Index: 2477231 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.5093. Min Act: -0.1700
Data Index: 4017528 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.4468. Min Act: -0.1700
Data Index: 1482164 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.4468. Min Act: -0.1700
Data Index: 399475 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.4156. Min Act: -0.1700
Data Index: 3936543 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.4156. Min Act: -0.1700
Data Index: 22927 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.3843. Min Act: -0.1700
Data Index: 2939915 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.3843. Min Act: -0.1700
Data Index: 5115901 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.3531. Min Act: -0.1700
Data Index: 6586002 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.3843. Min Act: -0.1700
Data Index: 6676893 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.3531. Min Act: -0.1700
Data Index: 805401 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.3531. Min Act: -0.1700
Data Index: 3833631 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.3531. Min Act: -0.1700
Data Index: 4570359 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19