Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3061 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3888. Min Range: -7.3888
Max Act: 7.3888. Min Act: -0.1700
Data Index: 5822768 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3888. Min Range: -7.3888
Max Act: 7.0763. Min Act: -0.1700
Data Index: 3881759 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.9825. Min Act: -0.1700
Data Index: 8685562 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.9200. Min Act: -0.1700
Data Index: 5822761 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.7950. Min Act: -0.1700
Data Index: 5822760 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.8263. Min Act: -0.1700
Data Index: 2276975 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.8263. Min Act: -0.1700
Data Index: 5822762 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.7325. Min Act: -0.1700
Data Index: 6160295 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.7325. Min Act: -0.1700
Data Index: 3876948 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6700. Min Act: -0.1700
Data Index: 8121188 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6388. Min Act: -0.1700
Data Index: 7383978 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6700. Min Act: -0.1700
Data Index: 4239211 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6388. Min Act: -0.1700
Data Index: 6875005 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6388. Min Act: -0.1700
Data Index: 1140028 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6075. Min Act: -0.1700
Data Index: 6555947 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6075. Min Act: -0.1700
Data Index: 5854646 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6075. Min Act: -0.1700
Data Index: 2246180 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6075. Min Act: -0.1700
Data Index: 2643959 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6075. Min Act: -0.1700
Data Index: 3035074 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3888. Min Range: -7.3888
Max Act: 6.6075. Min Act: -0.1700
Data Index: 8198735 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19