Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1538 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.3494. Min Act: -0.1700
Data Index: 5488996 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.3182. Min Act: -0.1700
Data Index: 5129613 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.2869. Min Act: -0.1700
Data Index: 2805260 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.2557. Min Act: -0.1700
Data Index: 3347993 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.1932. Min Act: -0.1700
Data Index: 7254456 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.1619. Min Act: -0.1700
Data Index: 3595379 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.1619. Min Act: -0.1700
Data Index: 4391130 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.1307. Min Act: -0.1700
Data Index: 7930133 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.1307. Min Act: -0.1700
Data Index: 6877703 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0994. Min Act: -0.1700
Data Index: 7755715 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0994. Min Act: -0.1700
Data Index: 7244313 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0682. Min Act: -0.1700
Data Index: 4840092 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0682. Min Act: -0.1700
Data Index: 2013427 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0682. Min Act: -0.1700
Data Index: 6927868 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0682. Min Act: -0.1700
Data Index: 3402145 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0682. Min Act: -0.1700
Data Index: 3554978 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0682. Min Act: -0.1700
Data Index: 6985858 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0682. Min Act: -0.1700
Data Index: 2262315 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0369. Min Act: -0.1700
Data Index: 5488988 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3494. Min Range: -6.3494
Max Act: 6.0369. Min Act: -0.1700
Data Index: 1917014 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19