Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4594. Min Range: -9.4594
Max Act: 9.4594. Min Act: -0.1700
Data Index: 6108024 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4594. Min Range: -9.4594
Max Act: 9.0219. Min Act: -0.1700
Data Index: 4656376 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.9594. Min Act: -0.1700
Data Index: 5543815 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.9594. Min Act: -0.1700
Data Index: 7398501 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.8969. Min Act: -0.1700
Data Index: 1493613 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.8969. Min Act: -0.1700
Data Index: 3068823 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.8969. Min Act: -0.1700
Data Index: 7462197 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.8344. Min Act: -0.1700
Data Index: 804527 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.8344. Min Act: -0.1700
Data Index: 3915793 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.8344. Min Act: -0.1700
Data Index: 5637545 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.7719. Min Act: -0.1700
Data Index: 2697193 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.7719. Min Act: -0.1700
Data Index: 3555462 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.7719. Min Act: -0.1700
Data Index: 8701255 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.7094. Min Act: -0.1700
Data Index: 6015874 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.7094. Min Act: -0.1700
Data Index: 8170037 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.6469. Min Act: -0.1700
Data Index: 2806960 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.6469. Min Act: -0.1700
Data Index: 647240 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.6469. Min Act: -0.1700
Data Index: 4703112 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.6469. Min Act: -0.1700
Data Index: 1190106 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4594. Min Range: -9.4594
Max Act: 8.5844. Min Act: -0.1700
Data Index: 4508130 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19