Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.7442. Min Act: -0.1700
Data Index: 5061723 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.6817. Min Act: -0.1700
Data Index: 5061725 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.5879. Min Act: -0.1700
Data Index: 5061726 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.5567. Min Act: -0.1700
Data Index: 3844267 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.5567. Min Act: -0.1700
Data Index: 6442555 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4942. Min Act: -0.1700
Data Index: 5916188 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4942. Min Act: -0.1700
Data Index: 4077680 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4942. Min Act: -0.1700
Data Index: 1501259 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4629. Min Act: -0.1700
Data Index: 144419 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4629. Min Act: -0.1700
Data Index: 1384364 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4629. Min Act: -0.1700
Data Index: 5362409 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4629. Min Act: -0.1700
Data Index: 8572681 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4317. Min Act: -0.1700
Data Index: 1145197 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4629. Min Act: -0.1700
Data Index: 2620281 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4629. Min Act: -0.1700
Data Index: 2357208 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4317. Min Act: -0.1700
Data Index: 6786892 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4317. Min Act: -0.1700
Data Index: 2357206 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4317. Min Act: -0.1700
Data Index: 2357204 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4317. Min Act: -0.1700
Data Index: 1469484 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7442. Min Range: -5.7442
Max Act: 5.4004. Min Act: -0.1700
Data Index: 1365750 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19