Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.2006. Min Act: -0.1700
Data Index: 1325554 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.1069. Min Act: -0.1700
Data Index: 5232713 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.1069. Min Act: -0.1700
Data Index: 8197326 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.1069. Min Act: -0.1700
Data Index: 8037274 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.1069. Min Act: -0.1700
Data Index: 5933802 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.1069. Min Act: -0.1700
Data Index: 5227510 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.1069. Min Act: -0.1700
Data Index: 2830289 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.0756. Min Act: -0.1700
Data Index: 2626171 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.0756. Min Act: -0.1700
Data Index: 335562 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.0444. Min Act: -0.1700
Data Index: 798583 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.0444. Min Act: -0.1700
Data Index: 1248108 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.0131. Min Act: -0.1700
Data Index: 7661781 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.9819. Min Act: -0.1700
Data Index: 3806628 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.9819. Min Act: -0.1700
Data Index: 3278884 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2006. Min Range: -5.2006
Max Act: 5.0131. Min Act: -0.1700
Data Index: 671390 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.9819. Min Act: -0.1700
Data Index: 2439890 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.9819. Min Act: -0.1700
Data Index: 8631429 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.9819. Min Act: -0.1700
Data Index: 7799951 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.9819. Min Act: -0.1700
Data Index: 7999818 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2006. Min Range: -5.2006
Max Act: 4.9506. Min Act: -0.1700
Data Index: 4382042 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19