Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2382 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.4097. Min Act: -0.1700
Data Index: 101633 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.2535. Min Act: -0.1700
Data Index: 574497 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.1597. Min Act: -0.1700
Data Index: 6036008 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.1597. Min Act: -0.1700
Data Index: 1397820 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.0972. Min Act: -0.1700
Data Index: 6554548 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.0972. Min Act: -0.1700
Data Index: 7705588 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.0972. Min Act: -0.1700
Data Index: 355757 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.0660. Min Act: -0.1700
Data Index: 355758 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.0660. Min Act: -0.1700
Data Index: 6173432 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.0347. Min Act: -0.1700
Data Index: 7014313 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.0347. Min Act: -0.1700
Data Index: 3203528 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.0347. Min Act: -0.1700
Data Index: 244533 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4097. Min Range: -6.4097
Max Act: 6.0035. Min Act: -0.1700
Data Index: 6209879 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4097. Min Range: -6.4097
Max Act: 5.9722. Min Act: -0.1700
Data Index: 8070088 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4097. Min Range: -6.4097
Max Act: 5.9722. Min Act: -0.1700
Data Index: 5884147 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4097. Min Range: -6.4097
Max Act: 5.9097. Min Act: -0.1700
Data Index: 1904608 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4097. Min Range: -6.4097
Max Act: 5.9410. Min Act: -0.1700
Data Index: 2655171 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4097. Min Range: -6.4097
Max Act: 5.9097. Min Act: -0.1700
Data Index: 6025298 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4097. Min Range: -6.4097
Max Act: 5.8785. Min Act: -0.1700
Data Index: 7091864 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4097. Min Range: -6.4097
Max Act: 5.8785. Min Act: -0.1700
Data Index: 675336 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19