Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 595 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.2211. Min Act: -0.1700
Data Index: 1021709 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.2211. Min Act: -0.1700
Data Index: 6523926 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.1898. Min Act: -0.1700
Data Index: 4811503 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.1586. Min Act: -0.1700
Data Index: 7173102 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.1273. Min Act: -0.1700
Data Index: 5147818 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.0336. Min Act: -0.1700
Data Index: 1260098 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.0648. Min Act: -0.1700
Data Index: 457539 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.0023. Min Act: -0.1700
Data Index: 6070788 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.0023. Min Act: -0.1700
Data Index: 7588885 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.0023. Min Act: -0.1700
Data Index: 2166960 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.0023. Min Act: -0.1700
Data Index: 5557134 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2211. Min Range: -7.2211
Max Act: 7.0023. Min Act: -0.1700
Data Index: 7565022 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2211. Min Range: -7.2211
Max Act: 6.9711. Min Act: -0.1700
Data Index: 3693251 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2211. Min Range: -7.2211
Max Act: 6.9711. Min Act: -0.1700
Data Index: 3584458 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2211. Min Range: -7.2211
Max Act: 6.9086. Min Act: -0.1700
Data Index: 1241432 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2211. Min Range: -7.2211
Max Act: 6.9711. Min Act: -0.1700
Data Index: 8361056 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2211. Min Range: -7.2211
Max Act: 6.8773. Min Act: -0.1700
Data Index: 8099308 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2211. Min Range: -7.2211
Max Act: 6.8773. Min Act: -0.1700
Data Index: 1977425 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2211. Min Range: -7.2211
Max Act: 6.8461. Min Act: -0.1700
Data Index: 482844 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2211. Min Range: -7.2211
Max Act: 6.8461. Min Act: -0.1700
Data Index: 2532671 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19