Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4083 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.3267. Min Act: -0.1700
Data Index: 953280 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.2642. Min Act: -0.1700
Data Index: 5919275 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.2329. Min Act: -0.1700
Data Index: 2286461 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.2329. Min Act: -0.1700
Data Index: 8548880 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.2329. Min Act: -0.1700
Data Index: 8127107 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.2017. Min Act: -0.1700
Data Index: 7940343 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.2017. Min Act: -0.1700
Data Index: 8127110 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.1704. Min Act: -0.1700
Data Index: 4901280 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.1704. Min Act: -0.1700
Data Index: 6046419 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.1079. Min Act: -0.1700
Data Index: 4899281 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.1079. Min Act: -0.1700
Data Index: 2872052 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.1079. Min Act: -0.1700
Data Index: 6969462 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.0454. Min Act: -0.1700
Data Index: 6081089 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.0767. Min Act: -0.1700
Data Index: 7980074 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.0767. Min Act: -0.1700
Data Index: 4117854 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.0767. Min Act: -0.1700
Data Index: 670078 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.0454. Min Act: -0.1700
Data Index: 4152319 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.0454. Min Act: -0.1700
Data Index: 5025848 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.0454. Min Act: -0.1700
Data Index: 906000 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3267. Min Range: -4.3267
Max Act: 4.0141. Min Act: -0.1700
Data Index: 3494965 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19