Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3954 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.5692. Min Act: -0.1700
Data Index: 6261780 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.4755. Min Act: -0.1700
Data Index: 297779 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.4442. Min Act: -0.1700
Data Index: 4342693 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.4130. Min Act: -0.1700
Data Index: 1994319 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.4130. Min Act: -0.1700
Data Index: 7214718 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.4130. Min Act: -0.1700
Data Index: 2261086 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.4130. Min Act: -0.1700
Data Index: 4444340 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.4130. Min Act: -0.1700
Data Index: 7864119 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3817. Min Act: -0.1700
Data Index: 7096213 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3505. Min Act: -0.1700
Data Index: 5261282 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3817. Min Act: -0.1700
Data Index: 7982800 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3505. Min Act: -0.1700
Data Index: 4815487 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3505. Min Act: -0.1700
Data Index: 8821381 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3505. Min Act: -0.1700
Data Index: 5760932 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3505. Min Act: -0.1700
Data Index: 2925925 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3505. Min Act: -0.1700
Data Index: 3958736 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3192. Min Act: -0.1700
Data Index: 1856822 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3192. Min Act: -0.1700
Data Index: 2278133 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.3192. Min Act: -0.1700
Data Index: 6776458 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5692. Min Range: -5.5692
Max Act: 5.2880. Min Act: -0.1700
Data Index: 4094984 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19