Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2009. Min Range: -8.2009
Max Act: 8.2009. Min Act: -0.1700
Data Index: 7684009 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.9509. Min Act: -0.1700
Data Index: 2197007 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.8884. Min Act: -0.1700
Data Index: 295187 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.8884. Min Act: -0.1700
Data Index: 3646282 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.8259. Min Act: -0.1700
Data Index: 1146351 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.7634. Min Act: -0.1700
Data Index: 4750411 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.7009. Min Act: -0.1700
Data Index: 3093918 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.6384. Min Act: -0.1700
Data Index: 3768244 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.6384. Min Act: -0.1700
Data Index: 3612141 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.6384. Min Act: -0.1700
Data Index: 8756323 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.6071. Min Act: -0.1700
Data Index: 8218252 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.5134. Min Act: -0.1700
Data Index: 8166064 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.4821. Min Act: -0.1700
Data Index: 8756322 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.4821. Min Act: -0.1700
Data Index: 858178 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.3884. Min Act: -0.1700
Data Index: 7350466 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.3571. Min Act: -0.1700
Data Index: 7655716 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.3571. Min Act: -0.1700
Data Index: 1890708 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.3259. Min Act: -0.1700
Data Index: 3435064 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.3259. Min Act: -0.1700
Data Index: 3942431 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2009. Min Range: -8.2009
Max Act: 7.2634. Min Act: -0.1700
Data Index: 4760947 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19