Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.7215. Min Act: -0.1700
Data Index: 6303332 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.4090. Min Act: -0.1700
Data Index: 764075 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.3465. Min Act: -0.1700
Data Index: 3442568 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.3465. Min Act: -0.1700
Data Index: 7356295 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.2840. Min Act: -0.1700
Data Index: 7140106 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.2528. Min Act: -0.1700
Data Index: 633528 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.2528. Min Act: -0.1700
Data Index: 5041952 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1590. Min Act: -0.1700
Data Index: 5972997 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1903. Min Act: -0.1700
Data Index: 6418334 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1590. Min Act: -0.1700
Data Index: 5065053 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1903. Min Act: -0.1700
Data Index: 4521188 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1903. Min Act: -0.1700
Data Index: 8028963 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1590. Min Act: -0.1700
Data Index: 5273636 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1903. Min Act: -0.1700
Data Index: 3055128 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1590. Min Act: -0.1700
Data Index: 4195778 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1590. Min Act: -0.1700
Data Index: 6809531 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1278. Min Act: -0.1700
Data Index: 847991 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1278. Min Act: -0.1700
Data Index: 4995318 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.0965. Min Act: -0.1700
Data Index: 7810709 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.0340. Min Act: -0.1700
Data Index: 3688290 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19