Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5806 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.6294. Min Act: -0.1700
Data Index: 6103319 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.3482. Min Act: -0.1700
Data Index: 5392472 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.3169. Min Act: -0.1700
Data Index: 7639103 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.3169. Min Act: -0.1700
Data Index: 1095797 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.2857. Min Act: -0.1700
Data Index: 6234865 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.2857. Min Act: -0.1700
Data Index: 930490 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.2544. Min Act: -0.1700
Data Index: 1109025 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1919. Min Act: -0.1700
Data Index: 1775563 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.2232. Min Act: -0.1700
Data Index: 2279152 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1919. Min Act: -0.1700
Data Index: 760118 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1919. Min Act: -0.1700
Data Index: 6581796 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1919. Min Act: -0.1700
Data Index: 5972116 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1919. Min Act: -0.1700
Data Index: 7212337 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1919. Min Act: -0.1700
Data Index: 193750 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1919. Min Act: -0.1700
Data Index: 8183070 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1607. Min Act: -0.1700
Data Index: 4634885 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1607. Min Act: -0.1700
Data Index: 6742869 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1919. Min Act: -0.1700
Data Index: 1753358 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1607. Min Act: -0.1700
Data Index: 6356204 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6294. Min Range: -4.6294
Max Act: 4.1607. Min Act: -0.1700
Data Index: 6291019 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19