Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 379 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.8955. Min Act: -0.1700
Data Index: 299440 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.7080. Min Act: -0.1696
Data Index: 1766313 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.6455. Min Act: -0.1700
Data Index: 4321970 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.5830. Min Act: -0.1700
Data Index: 3319584 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.3330. Min Act: -0.1700
Data Index: 7473554 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.3955. Min Act: -0.1700
Data Index: 3684527 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.3955. Min Act: -0.1700
Data Index: 5242387 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.2705. Min Act: -0.1700
Data Index: 2114415 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.2705. Min Act: -0.1700
Data Index: 2437687 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.2080. Min Act: -0.1700
Data Index: 3755769 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.2080. Min Act: -0.1700
Data Index: 874637 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.1455. Min Act: -0.1700
Data Index: 7216307 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.1455. Min Act: -0.1699
Data Index: 4807162 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.1455. Min Act: -0.1698
Data Index: 647057 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.1455. Min Act: -0.1700
Data Index: 7537121 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.0830. Min Act: -0.1700
Data Index: 3511480 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.0830. Min Act: -0.1700
Data Index: 8691 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.0830. Min Act: -0.1700
Data Index: 2566149 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.0830. Min Act: -0.1700
Data Index: 2087203 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8955. Min Range: -9.8955
Max Act: 9.0830. Min Act: -0.1700
Data Index: 7228638 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19