Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4891 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.3901. Min Act: -0.1700
Data Index: 7925596 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.2645. Min Act: -0.1700
Data Index: 7689651 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.1702. Min Act: -0.1700
Data Index: 5980536 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.1545. Min Act: -0.1700
Data Index: 5425656 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.1545. Min Act: -0.1700
Data Index: 7920002 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.1387. Min Act: -0.1700
Data Index: 6146606 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.1387. Min Act: -0.1700
Data Index: 6231291 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.1230. Min Act: -0.1700
Data Index: 4001327 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.1230. Min Act: -0.1700
Data Index: 1833101 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.1230. Min Act: -0.1700
Data Index: 4517330 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.1072. Min Act: -0.1700
Data Index: 7481239 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.0914. Min Act: -0.1700
Data Index: 2432517 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.0914. Min Act: -0.1700
Data Index: 7493473 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.0757. Min Act: -0.1700
Data Index: 5500111 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.0757. Min Act: -0.1700
Data Index: 7542632 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.0757. Min Act: -0.1700
Data Index: 5455513 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.0599. Min Act: -0.1700
Data Index: 1938678 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.0599. Min Act: -0.1700
Data Index: 3187111 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.0599. Min Act: -0.1700
Data Index: 6467524 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3901. Min Range: -3.3901
Max Act: 3.0599. Min Act: -0.1700
Data Index: 4519070 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19