Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4684. Min Range: -6.4684
Max Act: 6.4684. Min Act: -0.1700
Data Index: 4936535 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4684. Min Range: -6.4684
Max Act: 6.3122. Min Act: -0.1700
Data Index: 6766496 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4684. Min Range: -6.4684
Max Act: 6.1872. Min Act: -0.1700
Data Index: 2126613 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4684. Min Range: -6.4684
Max Act: 6.0934. Min Act: -0.1700
Data Index: 1770437 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4684. Min Range: -6.4684
Max Act: 6.0309. Min Act: -0.1700
Data Index: 1275668 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9997. Min Act: -0.1700
Data Index: 4979391 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9684. Min Act: -0.1700
Data Index: 8638810 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9997. Min Act: -0.1700
Data Index: 5221007 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4684. Min Range: -6.4684
Max Act: 6.0309. Min Act: -0.1700
Data Index: 4373575 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9372. Min Act: -0.1700
Data Index: 1120727 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9372. Min Act: -0.1700
Data Index: 1668410 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9684. Min Act: -0.1700
Data Index: 8697572 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9684. Min Act: -0.1700
Data Index: 8435768 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9372. Min Act: -0.1700
Data Index: 7594388 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9059. Min Act: -0.1700
Data Index: 7890555 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9059. Min Act: -0.1700
Data Index: 5946991 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.9059. Min Act: -0.1700
Data Index: 3295908 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.8747. Min Act: -0.1700
Data Index: 3896335 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.8747. Min Act: -0.1700
Data Index: 2828541 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4684. Min Range: -6.4684
Max Act: 5.8747. Min Act: -0.1700
Data Index: 4730856 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19