Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5095 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1874. Min Range: -6.1874
Max Act: 6.1874. Min Act: -0.1700
Data Index: 5216536 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1874. Min Range: -6.1874
Max Act: 6.1562. Min Act: -0.1700
Data Index: 4615586 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1874. Min Range: -6.1874
Max Act: 6.1562. Min Act: -0.1700
Data Index: 6480167 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1874. Min Range: -6.1874
Max Act: 6.1249. Min Act: -0.1700
Data Index: 5430375 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1874. Min Range: -6.1874
Max Act: 6.0937. Min Act: -0.1700
Data Index: 7243597 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1874. Min Range: -6.1874
Max Act: 6.0624. Min Act: -0.1700
Data Index: 2669662 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1874. Min Range: -6.1874
Max Act: 6.0624. Min Act: -0.1700
Data Index: 8007203 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.9999. Min Act: -0.1700
Data Index: 1771799 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1874. Min Range: -6.1874
Max Act: 6.0312. Min Act: -0.1700
Data Index: 3410726 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.9999. Min Act: -0.1700
Data Index: 7560335 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.9374. Min Act: -0.1700
Data Index: 7939962 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.9687. Min Act: -0.1700
Data Index: 8827873 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.9687. Min Act: -0.1700
Data Index: 4486466 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.9062. Min Act: -0.1700
Data Index: 7978813 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.9062. Min Act: -0.1700
Data Index: 8398886 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.9062. Min Act: -0.1700
Data Index: 1560800 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.9062. Min Act: -0.1700
Data Index: 1311533 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.9062. Min Act: -0.1700
Data Index: 4809410 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.8749. Min Act: -0.1700
Data Index: 1111725 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1874. Min Range: -6.1874
Max Act: 5.8749. Min Act: -0.1700
Data Index: 3134034 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19