Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4823 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.5277. Min Act: -0.1700
Data Index: 4105708 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.4027. Min Act: -0.1700
Data Index: 6633773 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.2777. Min Act: -0.1700
Data Index: 4709486 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.2777. Min Act: -0.1700
Data Index: 1349607 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.2465. Min Act: -0.1700
Data Index: 3457173 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.1527. Min Act: -0.1700
Data Index: 735192 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.1840. Min Act: -0.1700
Data Index: 7064707 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.1215. Min Act: -0.1700
Data Index: 5675070 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.1527. Min Act: -0.1700
Data Index: 2728624 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.1527. Min Act: -0.1700
Data Index: 8234140 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.1215. Min Act: -0.1700
Data Index: 3882970 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.0590. Min Act: -0.1700
Data Index: 2294689 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.0277. Min Act: -0.1700
Data Index: 6780053 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.0590. Min Act: -0.1700
Data Index: 6754463 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5277. Min Range: -7.5277
Max Act: 7.0277. Min Act: -0.1700
Data Index: 2669523 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5277. Min Range: -7.5277
Max Act: 6.9652. Min Act: -0.1700
Data Index: 2277234 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5277. Min Range: -7.5277
Max Act: 6.9965. Min Act: -0.1700
Data Index: 7951587 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5277. Min Range: -7.5277
Max Act: 6.9652. Min Act: -0.1700
Data Index: 1945148 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5277. Min Range: -7.5277
Max Act: 6.9340. Min Act: -0.1700
Data Index: 5141847 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5277. Min Range: -7.5277
Max Act: 6.9027. Min Act: -0.1700
Data Index: 5503070 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19