Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.6946. Min Act: -0.1700
Data Index: 2574670 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.6633. Min Act: -0.1700
Data Index: 270121 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.6008. Min Act: -0.1700
Data Index: 4912774 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.6008. Min Act: -0.1700
Data Index: 1254318 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.6008. Min Act: -0.1700
Data Index: 1830176 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5696. Min Act: -0.1700
Data Index: 840665 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5383. Min Act: -0.1700
Data Index: 2912399 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5383. Min Act: -0.1700
Data Index: 3890200 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5383. Min Act: -0.1700
Data Index: 5243350 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5071. Min Act: -0.1700
Data Index: 4329916 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5071. Min Act: -0.1700
Data Index: 5873458 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5071. Min Act: -0.1700
Data Index: 6147693 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5071. Min Act: -0.1700
Data Index: 785642 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5071. Min Act: -0.1700
Data Index: 1454015 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5071. Min Act: -0.1700
Data Index: 1693792 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.4446. Min Act: -0.1700
Data Index: 6236782 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.4758. Min Act: -0.1700
Data Index: 5987350 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.5071. Min Act: -0.1700
Data Index: 6854753 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.4446. Min Act: -0.1699
Data Index: 200644 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6946. Min Range: -6.6946
Max Act: 6.4446. Min Act: -0.1700
Data Index: 2923141 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19