Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5896 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5996. Min Range: -7.5996
Max Act: 7.5996. Min Act: -0.1700
Data Index: 6953106 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5996. Min Range: -7.5996
Max Act: 7.3496. Min Act: -0.1700
Data Index: 5426178 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5996. Min Range: -7.5996
Max Act: 7.2871. Min Act: -0.1700
Data Index: 294082 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5996. Min Range: -7.5996
Max Act: 7.0683. Min Act: -0.1700
Data Index: 5447765 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5996. Min Range: -7.5996
Max Act: 7.0058. Min Act: -0.1700
Data Index: 79118 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5996. Min Range: -7.5996
Max Act: 7.0058. Min Act: -0.1700
Data Index: 4504175 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5996. Min Range: -7.5996
Max Act: 7.0058. Min Act: -0.1700
Data Index: 2570531 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5996. Min Range: -7.5996
Max Act: 7.0371. Min Act: -0.1700
Data Index: 3678784 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.9746. Min Act: -0.1700
Data Index: 2840558 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.9433. Min Act: -0.1700
Data Index: 6489199 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.9746. Min Act: -0.1700
Data Index: 5341462 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.9433. Min Act: -0.1700
Data Index: 2726752 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.9433. Min Act: -0.1700
Data Index: 612764 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.9121. Min Act: -0.1700
Data Index: 5602574 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.9121. Min Act: -0.1700
Data Index: 4514244 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.8808. Min Act: -0.1700
Data Index: 2809104 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.8808. Min Act: -0.1700
Data Index: 1894938 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.8496. Min Act: -0.1700
Data Index: 4010288 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.8183. Min Act: -0.1700
Data Index: 7665417 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5996. Min Range: -7.5996
Max Act: 6.8183. Min Act: -0.1700
Data Index: 2263516 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19