Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1741 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.6741. Min Act: -0.1700
Data Index: 7362892 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.6429. Min Act: -0.1700
Data Index: 7624090 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.5491. Min Act: -0.1700
Data Index: 3640136 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.5491. Min Act: -0.1700
Data Index: 6257483 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.5179. Min Act: -0.1700
Data Index: 7718121 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.5179. Min Act: -0.1700
Data Index: 8045396 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.3929. Min Act: -0.1700
Data Index: 4983645 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.4241. Min Act: -0.1700
Data Index: 1035734 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.3929. Min Act: -0.1700
Data Index: 2880645 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.3929. Min Act: -0.1700
Data Index: 6239732 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.3616. Min Act: -0.1700
Data Index: 7584065 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.2991. Min Act: -0.1700
Data Index: 3094070 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.2991. Min Act: -0.1700
Data Index: 8767890 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.2991. Min Act: -0.1700
Data Index: 1668417 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.2991. Min Act: -0.1700
Data Index: 8353633 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.2679. Min Act: -0.1700
Data Index: 5426650 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.2679. Min Act: -0.1700
Data Index: 2259756 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.2366. Min Act: -0.1700
Data Index: 5988685 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.2366. Min Act: -0.1700
Data Index: 6601785 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6741. Min Range: -5.6741
Max Act: 5.2366. Min Act: -0.1700
Data Index: 7174412 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19