Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4032. Min Range: -6.4032
Max Act: 6.4032. Min Act: -0.1700
Data Index: 6631102 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4032. Min Range: -6.4032
Max Act: 6.2470. Min Act: -0.1700
Data Index: 6158095 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4032. Min Range: -6.4032
Max Act: 6.0907. Min Act: -0.1700
Data Index: 521067 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4032. Min Range: -6.4032
Max Act: 6.0595. Min Act: -0.1700
Data Index: 6364830 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.9657. Min Act: -0.1700
Data Index: 714990 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.9345. Min Act: -0.1700
Data Index: 8355834 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.9345. Min Act: -0.1700
Data Index: 4839844 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.8095. Min Act: -0.1700
Data Index: 1596859 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.8095. Min Act: -0.1700
Data Index: 4681074 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.8095. Min Act: -0.1700
Data Index: 4180540 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.8095. Min Act: -0.1700
Data Index: 4473800 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.7470. Min Act: -0.1700
Data Index: 323528 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.7470. Min Act: -0.1700
Data Index: 5996513 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.7470. Min Act: -0.1700
Data Index: 4900257 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.7470. Min Act: -0.1700
Data Index: 3062486 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.7157. Min Act: -0.1700
Data Index: 1310796 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.7157. Min Act: -0.1700
Data Index: 3539310 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.6845. Min Act: -0.1700
Data Index: 3082458 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.6532. Min Act: -0.1700
Data Index: 8294232 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4032. Min Range: -6.4032
Max Act: 5.6532. Min Act: -0.1700
Data Index: 4600005 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19