Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1054 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.3032. Min Act: -0.1700
Data Index: 864948 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.3032. Min Act: -0.1700
Data Index: 4656331 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.1782. Min Act: -0.1700
Data Index: 737710 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.1470. Min Act: -0.1700
Data Index: 1395969 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.1470. Min Act: -0.1700
Data Index: 3579724 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.1157. Min Act: -0.1700
Data Index: 3690795 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.1157. Min Act: -0.1700
Data Index: 1128820 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.0845. Min Act: -0.1700
Data Index: 5199709 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.0532. Min Act: -0.1700
Data Index: 2657884 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.0219. Min Act: -0.1700
Data Index: 2044876 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.0219. Min Act: -0.1700
Data Index: 4866518 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3032. Min Range: -4.3032
Max Act: 3.9907. Min Act: -0.1700
Data Index: 875485 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.0219. Min Act: -0.1700
Data Index: 4113367 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.0219. Min Act: -0.1700
Data Index: 8474779 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.0219. Min Act: -0.1700
Data Index: 1128821 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3032. Min Range: -4.3032
Max Act: 4.0219. Min Act: -0.1700
Data Index: 1390377 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3032. Min Range: -4.3032
Max Act: 3.9907. Min Act: -0.1700
Data Index: 872367 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3032. Min Range: -4.3032
Max Act: 3.9907. Min Act: -0.1700
Data Index: 1105986 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3032. Min Range: -4.3032
Max Act: 3.9907. Min Act: -0.1700
Data Index: 5560630 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3032. Min Range: -4.3032
Max Act: 3.9907. Min Act: -0.1700
Data Index: 5654387 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19