Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4421 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0814. Min Range: -7.0814
Max Act: 7.0814. Min Act: -0.1700
Data Index: 6026756 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0814. Min Range: -7.0814
Max Act: 7.0814. Min Act: -0.1700
Data Index: 6026733 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.7689. Min Act: -0.1700
Data Index: 8200108 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.6127. Min Act: -0.1700
Data Index: 7420739 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.6127. Min Act: -0.1700
Data Index: 6007575 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.5814. Min Act: -0.1700
Data Index: 5879904 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.5814. Min Act: -0.1700
Data Index: 4373701 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.4877. Min Act: -0.1700
Data Index: 5953188 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.4877. Min Act: -0.1700
Data Index: 7708577 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.4564. Min Act: -0.1700
Data Index: 5272191 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.4252. Min Act: -0.1700
Data Index: 3750683 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.4252. Min Act: -0.1700
Data Index: 329835 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.3939. Min Act: -0.1700
Data Index: 7642184 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.3939. Min Act: -0.1700
Data Index: 7095043 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.3627. Min Act: -0.1700
Data Index: 2194805 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.3627. Min Act: -0.1700
Data Index: 1121945 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.3627. Min Act: -0.1700
Data Index: 7708576 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.3314. Min Act: -0.1700
Data Index: 557579 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.2689. Min Act: -0.1700
Data Index: 3725892 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.3002. Min Act: -0.1700
Data Index: 2561657 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19