Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 856 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.4824. Min Act: -0.1700
Data Index: 8330753 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.3887. Min Act: -0.1700
Data Index: 1627591 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.3574. Min Act: -0.1700
Data Index: 3349686 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.3262. Min Act: -0.1700
Data Index: 5807852 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.2012. Min Act: -0.1700
Data Index: 2269250 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.2012. Min Act: -0.1700
Data Index: 1581887 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.1699. Min Act: -0.1700
Data Index: 6822887 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.1387. Min Act: -0.1700
Data Index: 4711602 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.1387. Min Act: -0.1700
Data Index: 6459510 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.1387. Min Act: -0.1700
Data Index: 3858867 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.1387. Min Act: -0.1700
Data Index: 6653680 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.0762. Min Act: -0.1700
Data Index: 7645058 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.0762. Min Act: -0.1700
Data Index: 3109703 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.0449. Min Act: -0.1700
Data Index: 1178930 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.0762. Min Act: -0.1700
Data Index: 3969121 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.0449. Min Act: -0.1700
Data Index: 698380 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.0762. Min Act: -0.1700
Data Index: 2546266 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.0137. Min Act: -0.1700
Data Index: 2354028 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.0137. Min Act: -0.1700
Data Index: 19372 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4824. Min Range: -6.4824
Max Act: 6.0137. Min Act: -0.1700
Data Index: 1918810 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19