Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6134 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1844. Min Range: -11.1844
Max Act: 11.1844. Min Act: -0.1700
Data Index: 6479112 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.6219. Min Act: -0.1700
Data Index: 5481851 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.4969. Min Act: -0.1700
Data Index: 2664783 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.3094. Min Act: -0.1700
Data Index: 8518117 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.2469. Min Act: -0.1700
Data Index: 7271845 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.1219. Min Act: -0.1700
Data Index: 4236044 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.1219. Min Act: -0.1700
Data Index: 3406375 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.0594. Min Act: -0.1700
Data Index: 3619672 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.0594. Min Act: -0.1700
Data Index: 4954977 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.0594. Min Act: -0.1700
Data Index: 7015970 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.0594. Min Act: -0.1700
Data Index: 3949046 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1844. Min Range: -11.1844
Max Act: 9.9969. Min Act: -0.1700
Data Index: 5964601 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1844. Min Range: -11.1844
Max Act: 9.9969. Min Act: -0.1700
Data Index: 4452839 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1844. Min Range: -11.1844
Max Act: 9.9969. Min Act: -0.1700
Data Index: 3743690 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1844. Min Range: -11.1844
Max Act: 9.9969. Min Act: -0.1700
Data Index: 2629814 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1844. Min Range: -11.1844
Max Act: 9.9344. Min Act: -0.1700
Data Index: 2598851 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1844. Min Range: -11.1844
Max Act: 9.9344. Min Act: -0.1700
Data Index: 5377375 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1844. Min Range: -11.1844
Max Act: 9.9344. Min Act: -0.1700
Data Index: 4347569 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1844. Min Range: -11.1844
Max Act: 9.9344. Min Act: -0.1700
Data Index: 4540877 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1844. Min Range: -11.1844
Max Act: 9.9344. Min Act: -0.1700
Data Index: 868868 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19