Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0957. Min Range: -5.0957
Max Act: 5.0957. Min Act: -0.1700
Data Index: 6352169 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.8769. Min Act: -0.1700
Data Index: 849131 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.8144. Min Act: -0.1700
Data Index: 1121039 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.7832. Min Act: -0.1700
Data Index: 936949 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.7519. Min Act: -0.1700
Data Index: 4608157 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6894. Min Act: -0.1700
Data Index: 104497 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6894. Min Act: -0.1700
Data Index: 1936118 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6582. Min Act: -0.1700
Data Index: 4745422 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6582. Min Act: -0.1700
Data Index: 73608 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6582. Min Act: -0.1700
Data Index: 531669 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6582. Min Act: -0.1700
Data Index: 5346422 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6269. Min Act: -0.1700
Data Index: 3157004 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6269. Min Act: -0.1700
Data Index: 1678793 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6269. Min Act: -0.1700
Data Index: 8272224 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6269. Min Act: -0.1700
Data Index: 2991934 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6269. Min Act: -0.1700
Data Index: 548677 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6269. Min Act: -0.1700
Data Index: 1570411 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.6269. Min Act: -0.1700
Data Index: 4324705 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.5957. Min Act: -0.1700
Data Index: 4971308 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0957. Min Range: -5.0957
Max Act: 4.5957. Min Act: -0.1700
Data Index: 1083100 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19