Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4096 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0854. Min Range: -9.0854
Max Act: 9.0854. Min Act: -0.1700
Data Index: 8476108 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.5854. Min Act: -0.1700
Data Index: 6181798 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.3979. Min Act: -0.1700
Data Index: 4135916 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.2729. Min Act: -0.1700
Data Index: 3997283 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.2729. Min Act: -0.1700
Data Index: 4996840 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.2104. Min Act: -0.1700
Data Index: 8806472 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.1479. Min Act: -0.1700
Data Index: 595977 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.1479. Min Act: -0.1700
Data Index: 1840821 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.1479. Min Act: -0.1700
Data Index: 7702355 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.1479. Min Act: -0.1700
Data Index: 7266276 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.0854. Min Act: -0.1700
Data Index: 5782387 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.1167. Min Act: -0.1700
Data Index: 2657229 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.0854. Min Act: -0.1700
Data Index: 2853107 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.1167. Min Act: -0.1700
Data Index: 1985874 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.0542. Min Act: -0.1700
Data Index: 612312 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.0854. Min Act: -0.1700
Data Index: 3414959 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.1167. Min Act: -0.1700
Data Index: 776312 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.0854. Min Act: -0.1700
Data Index: 776313 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.0229. Min Act: -0.1700
Data Index: 7312189 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0854. Min Range: -9.0854
Max Act: 8.0229. Min Act: -0.1700
Data Index: 2470388 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19