Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.9540. Min Act: -0.1700
Data Index: 4478219 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.9540. Min Act: -0.1700
Data Index: 3826943 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.8290. Min Act: -0.1700
Data Index: 4751357 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.8290. Min Act: -0.1700
Data Index: 4048228 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.5790. Min Act: -0.1700
Data Index: 746161 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.4540. Min Act: -0.1700
Data Index: 5170379 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.3915. Min Act: -0.1700
Data Index: 4308348 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.3915. Min Act: -0.1700
Data Index: 7762053 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.3915. Min Act: -0.1700
Data Index: 3091903 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.3290. Min Act: -0.1700
Data Index: 7401915 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.3290. Min Act: -0.1700
Data Index: 5634271 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.3290. Min Act: -0.1700
Data Index: 1718225 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.2040. Min Act: -0.1700
Data Index: 5305698 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.2040. Min Act: -0.1700
Data Index: 3900941 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.2040. Min Act: -0.1700
Data Index: 4244505 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.1415. Min Act: -0.1700
Data Index: 2296616 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.1415. Min Act: -0.1700
Data Index: 4215538 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.1415. Min Act: -0.1700
Data Index: 971097 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.0790. Min Act: -0.1700
Data Index: 1937157 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9540. Min Range: -8.9540
Max Act: 8.0790. Min Act: -0.1700
Data Index: 7968780 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19