Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3726 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9526. Min Range: -7.9526
Max Act: 7.9526. Min Act: -0.1700
Data Index: 8184133 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9526. Min Range: -7.9526
Max Act: 7.3901. Min Act: -0.1700
Data Index: 430688 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9526. Min Range: -7.9526
Max Act: 7.2339. Min Act: -0.1700
Data Index: 1549762 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9526. Min Range: -7.9526
Max Act: 7.0151. Min Act: -0.1700
Data Index: 377967 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.9839. Min Act: -0.1700
Data Index: 8587138 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.9526. Min Act: -0.1700
Data Index: 166502 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.9214. Min Act: -0.1700
Data Index: 2962328 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.8901. Min Act: -0.1700
Data Index: 2928405 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.8589. Min Act: -0.1700
Data Index: 1046941 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.8589. Min Act: -0.1700
Data Index: 2965623 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.8276. Min Act: -0.1700
Data Index: 6514931 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.8276. Min Act: -0.1700
Data Index: 5700455 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.8276. Min Act: -0.1700
Data Index: 3227994 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.7964. Min Act: -0.1700
Data Index: 7237583 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.7964. Min Act: -0.1700
Data Index: 1585199 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.8276. Min Act: -0.1700
Data Index: 1585983 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.7026. Min Act: -0.1700
Data Index: 4291762 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.7651. Min Act: -0.1700
Data Index: 1968045 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.7026. Min Act: -0.1700
Data Index: 4042095 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9526. Min Range: -7.9526
Max Act: 6.7026. Min Act: -0.1700
Data Index: 2737092 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19