Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4913 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.6632. Min Act: -0.1700
Data Index: 4457884 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.5382. Min Act: -0.1700
Data Index: 2949840 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.4132. Min Act: -0.1700
Data Index: 952779 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.3507. Min Act: -0.1700
Data Index: 2563187 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.2257. Min Act: -0.1700
Data Index: 8336789 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.1945. Min Act: -0.1700
Data Index: 2563185 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.1632. Min Act: -0.1700
Data Index: 2901294 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.1320. Min Act: -0.1700
Data Index: 5071025 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.1320. Min Act: -0.1700
Data Index: 3728150 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.1007. Min Act: -0.1700
Data Index: 6530439 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.0695. Min Act: -0.1700
Data Index: 8098828 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.1007. Min Act: -0.1700
Data Index: 489104 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.1007. Min Act: -0.1700
Data Index: 2474560 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.1007. Min Act: -0.1700
Data Index: 7197796 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.1007. Min Act: -0.1700
Data Index: 6279785 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.0695. Min Act: -0.1700
Data Index: 6303159 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.0695. Min Act: -0.1700
Data Index: 2474600 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.0695. Min Act: -0.1700
Data Index: 6633247 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.0695. Min Act: -0.1700
Data Index: 4141524 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6632. Min Range: -5.6632
Max Act: 5.0695. Min Act: -0.1700
Data Index: 4648974 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19