Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6070 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.4137. Min Act: -0.1700
Data Index: 5063770 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.1325. Min Act: -0.1700
Data Index: 3505147 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.1012. Min Act: -0.1700
Data Index: 3437903 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.1012. Min Act: -0.1700
Data Index: 5811633 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.1325. Min Act: -0.1700
Data Index: 79410 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.1012. Min Act: -0.1700
Data Index: 503100 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.1012. Min Act: -0.1700
Data Index: 312337 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0700. Min Act: -0.1700
Data Index: 68499 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.1012. Min Act: -0.1700
Data Index: 8033031 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0700. Min Act: -0.1700
Data Index: 4872095 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0700. Min Act: -0.1700
Data Index: 392463 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0700. Min Act: -0.1700
Data Index: 3173608 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0387. Min Act: -0.1700
Data Index: 8496776 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0387. Min Act: -0.1700
Data Index: 7697831 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0700. Min Act: -0.1700
Data Index: 3176787 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0387. Min Act: -0.1700
Data Index: 7144614 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0387. Min Act: -0.1700
Data Index: 2728459 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0387. Min Act: -0.1700
Data Index: 5074079 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0387. Min Act: -0.1700
Data Index: 1808979 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4137. Min Range: -4.4137
Max Act: 4.0074. Min Act: -0.1700
Data Index: 5660985 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19