Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.4887. Min Act: -0.1700
Data Index: 1051264 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.3637. Min Act: -0.1700
Data Index: 6175421 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.3637. Min Act: -0.1700
Data Index: 7465180 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.3637. Min Act: -0.1700
Data Index: 4541867 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.3324. Min Act: -0.1700
Data Index: 1473903 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.3012. Min Act: -0.1700
Data Index: 6003550 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.2699. Min Act: -0.1700
Data Index: 6803554 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.2699. Min Act: -0.1700
Data Index: 7862885 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.3012. Min Act: -0.1700
Data Index: 8714407 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.2074. Min Act: -0.1700
Data Index: 5189041 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.2074. Min Act: -0.1700
Data Index: 2454650 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.2387. Min Act: -0.1700
Data Index: 4923661 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.2387. Min Act: -0.1700
Data Index: 8349034 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.2074. Min Act: -0.1700
Data Index: 3979906 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.2074. Min Act: -0.1700
Data Index: 4648102 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.1449. Min Act: -0.1700
Data Index: 5534604 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.1449. Min Act: -0.1700
Data Index: 235602 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.1449. Min Act: -0.1700
Data Index: 620331 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.0824. Min Act: -0.1700
Data Index: 1490857 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4887. Min Range: -5.4887
Max Act: 5.1137. Min Act: -0.1700
Data Index: 7531172 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19