Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.9265. Min Act: -0.1700
Data Index: 3236153 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.9265. Min Act: -0.1700
Data Index: 5279667 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.8328. Min Act: -0.1700
Data Index: 2363020 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.8015. Min Act: -0.1700
Data Index: 882080 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.8015. Min Act: -0.1700
Data Index: 4645426 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.7078. Min Act: -0.1700
Data Index: 3106214 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.6765. Min Act: -0.1700
Data Index: 1245041 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.6453. Min Act: -0.1700
Data Index: 1697944 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.6140. Min Act: -0.1700
Data Index: 5400437 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.5515. Min Act: -0.1700
Data Index: 300793 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.5828. Min Act: -0.1700
Data Index: 2192219 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.5515. Min Act: -0.1700
Data Index: 5896590 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.5203. Min Act: -0.1700
Data Index: 7288488 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.5203. Min Act: -0.1700
Data Index: 5752706 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.5515. Min Act: -0.1700
Data Index: 1813428 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.4890. Min Act: -0.1700
Data Index: 206157 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.4578. Min Act: -0.1700
Data Index: 4888250 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.4578. Min Act: -0.1700
Data Index: 1295728 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.4265. Min Act: -0.1700
Data Index: 2050772 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9265. Min Range: -6.9265
Max Act: 6.4578. Min Act: -0.1700
Data Index: 6578780 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19