Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1182 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3929. Min Act: -0.1700
Data Index: 4348516 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3841. Min Act: -0.1685
Data Index: 7588270 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1700
Data Index: 116238 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1700
Data Index: 811136 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1700
Data Index: 498665 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1700
Data Index: 1148803 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1700
Data Index: 300200 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1698
Data Index: 792112 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1692
Data Index: 754510 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1700
Data Index: 1084470 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1697
Data Index: 244703 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1690
Data Index: 641031 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1696
Data Index: 993030 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1700
Data Index: 940561 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1689
Data Index: 445646 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1697
Data Index: 604709 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1662
Data Index: 12825 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1700
Data Index: 564709 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1700
Data Index: 1150131 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3929. Min Range: -1.3929
Max Act: 1.3753. Min Act: -0.1700
Data Index: 916352 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19