Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4061 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6844. Min Range: -8.6844
Max Act: 8.6844. Min Act: -0.1700
Data Index: 5678728 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.7469. Min Act: -0.1700
Data Index: 1594650 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.5907. Min Act: -0.1700
Data Index: 6415651 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.5594. Min Act: -0.1700
Data Index: 8191062 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.3094. Min Act: -0.1700
Data Index: 4927385 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.2469. Min Act: -0.1700
Data Index: 8580162 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.1844. Min Act: -0.1700
Data Index: 514010 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.1844. Min Act: -0.1700
Data Index: 8822704 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.1844. Min Act: -0.1700
Data Index: 3914615 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.1532. Min Act: -0.1700
Data Index: 2688920 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.1532. Min Act: -0.1700
Data Index: 3805595 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.1219. Min Act: -0.1700
Data Index: 4178488 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.1219. Min Act: -0.1700
Data Index: 476939 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.1219. Min Act: -0.1700
Data Index: 8594446 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.0594. Min Act: -0.1700
Data Index: 7342220 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.0282. Min Act: -0.1700
Data Index: 8345083 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6844. Min Range: -8.6844
Max Act: 7.0282. Min Act: -0.1700
Data Index: 1348650 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6844. Min Range: -8.6844
Max Act: 6.9969. Min Act: -0.1700
Data Index: 896627 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6844. Min Range: -8.6844
Max Act: 6.9969. Min Act: -0.1700
Data Index: 5527980 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6844. Min Range: -8.6844
Max Act: 6.9657. Min Act: -0.1700
Data Index: 7963861 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19