Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1594. Min Range: -7.1594
Max Act: 7.1594. Min Act: -0.1700
Data Index: 8475824 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1594. Min Range: -7.1594
Max Act: 7.1594. Min Act: -0.1700
Data Index: 4734586 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.9719. Min Act: -0.1700
Data Index: 6112262 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.9407. Min Act: -0.1700
Data Index: 749969 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.9094. Min Act: -0.1700
Data Index: 5536782 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.8157. Min Act: -0.1700
Data Index: 8574514 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.7844. Min Act: -0.1700
Data Index: 3544798 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.7532. Min Act: -0.1700
Data Index: 5417762 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.6907. Min Act: -0.1700
Data Index: 1165515 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.6907. Min Act: -0.1700
Data Index: 6095748 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.6282. Min Act: -0.1700
Data Index: 1180699 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.6282. Min Act: -0.1700
Data Index: 2330214 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.5969. Min Act: -0.1700
Data Index: 5028871 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.5969. Min Act: -0.1700
Data Index: 428841 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.5657. Min Act: -0.1700
Data Index: 727566 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.5657. Min Act: -0.1700
Data Index: 7913869 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.5657. Min Act: -0.1700
Data Index: 1895249 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.5344. Min Act: -0.1700
Data Index: 5688000 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.5344. Min Act: -0.1700
Data Index: 1038599 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1594. Min Range: -7.1594
Max Act: 6.5344. Min Act: -0.1700
Data Index: 8451341 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19