Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0592. Min Range: -6.0592
Max Act: 6.0592. Min Act: -0.1700
Data Index: 5588849 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.8717. Min Act: -0.1700
Data Index: 1330280 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.8404. Min Act: -0.1700
Data Index: 3894975 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.8092. Min Act: -0.1700
Data Index: 4891476 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.7779. Min Act: -0.1700
Data Index: 3160340 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.5904. Min Act: -0.1700
Data Index: 7987858 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.5904. Min Act: -0.1700
Data Index: 4633841 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.5279. Min Act: -0.1700
Data Index: 2019042 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.5904. Min Act: -0.1700
Data Index: 6784858 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.4967. Min Act: -0.1699
Data Index: 6555997 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.5279. Min Act: -0.1700
Data Index: 406694 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.4967. Min Act: -0.1700
Data Index: 7631004 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.4342. Min Act: -0.1700
Data Index: 2734614 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.4029. Min Act: -0.1700
Data Index: 4649641 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.4342. Min Act: -0.1700
Data Index: 2734609 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.4654. Min Act: -0.1700
Data Index: 872340 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.4342. Min Act: -0.1700
Data Index: 6110977 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.4029. Min Act: -0.1700
Data Index: 5387548 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.3717. Min Act: -0.1700
Data Index: 525323 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0592. Min Range: -6.0592
Max Act: 5.4029. Min Act: -0.1700
Data Index: 7252109 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19