Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0530. Min Range: -4.0530
Max Act: 4.0530. Min Act: -0.1700
Data Index: 1237388 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.9279. Min Act: -0.1700
Data Index: 6880834 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.8654. Min Act: -0.1700
Data Index: 6880835 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.8341. Min Act: -0.1700
Data Index: 2345639 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.8341. Min Act: -0.1700
Data Index: 5890129 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.8028. Min Act: -0.1700
Data Index: 6880825 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.7716. Min Act: -0.1700
Data Index: 6880827 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.7403. Min Act: -0.1700
Data Index: 6880826 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.7716. Min Act: -0.1700
Data Index: 4898160 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.7090. Min Act: -0.1700
Data Index: 7397918 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.7090. Min Act: -0.1700
Data Index: 6086653 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.6934. Min Act: -0.1700
Data Index: 6910379 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.6934. Min Act: -0.1700
Data Index: 5580809 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.6777. Min Act: -0.1700
Data Index: 1237387 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.6621. Min Act: -0.1700
Data Index: 4129990 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.6308. Min Act: -0.1700
Data Index: 7779999 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.6464. Min Act: -0.1700
Data Index: 2829369 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.6308. Min Act: -0.1700
Data Index: 5335957 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.6308. Min Act: -0.1700
Data Index: 1237390 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0530. Min Range: -4.0530
Max Act: 3.6308. Min Act: -0.1700
Data Index: 6677452 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19