Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.9738. Min Act: -0.1700
Data Index: 1483442 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.9113. Min Act: -0.1700
Data Index: 4498493 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.8488. Min Act: -0.1700
Data Index: 389848 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.8488. Min Act: -0.1700
Data Index: 5591622 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.7863. Min Act: -0.1700
Data Index: 5171799 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.7238. Min Act: -0.1700
Data Index: 6090928 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.6613. Min Act: -0.1700
Data Index: 5171793 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.6613. Min Act: -0.1700
Data Index: 3225831 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.6613. Min Act: -0.1700
Data Index: 188407 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.5988. Min Act: -0.1700
Data Index: 410559 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.6613. Min Act: -0.1700
Data Index: 7951113 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.5988. Min Act: -0.1700
Data Index: 198314 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.6613. Min Act: -0.1700
Data Index: 2258352 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.5988. Min Act: -0.1700
Data Index: 4690736 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.5988. Min Act: -0.1700
Data Index: 2547689 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.5988. Min Act: -0.1700
Data Index: 584487 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.5988. Min Act: -0.1700
Data Index: 4547200 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.5363. Min Act: -0.1700
Data Index: 1718313 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.4738. Min Act: -0.1700
Data Index: 4743996 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9738. Min Range: -8.9738
Max Act: 8.4738. Min Act: -0.1700
Data Index: 481862 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19