Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5390. Min Range: -8.5390
Max Act: 8.5390. Min Act: -0.1700
Data Index: 413021 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.9765. Min Act: -0.1700
Data Index: 8467735 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.6952. Min Act: -0.1700
Data Index: 4163054 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.6640. Min Act: -0.1700
Data Index: 4855595 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.5702. Min Act: -0.1700
Data Index: 8459115 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.4765. Min Act: -0.1700
Data Index: 8212685 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.4765. Min Act: -0.1700
Data Index: 6278050 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.4140. Min Act: -0.1700
Data Index: 4929469 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.4452. Min Act: -0.1700
Data Index: 407907 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.3827. Min Act: -0.1700
Data Index: 6884547 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.3827. Min Act: -0.1700
Data Index: 890293 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.3202. Min Act: -0.1700
Data Index: 3613118 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.3202. Min Act: -0.1700
Data Index: 5591065 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.2890. Min Act: -0.1700
Data Index: 4750341 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.3202. Min Act: -0.1700
Data Index: 4146611 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.2577. Min Act: -0.1700
Data Index: 2152689 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.2577. Min Act: -0.1700
Data Index: 2120285 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.1952. Min Act: -0.1700
Data Index: 237420 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.1640. Min Act: -0.1700
Data Index: 7707892 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5390. Min Range: -8.5390
Max Act: 7.1952. Min Act: -0.1700
Data Index: 6150126 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19