Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4909 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.5233. Min Act: -0.1700
Data Index: 6981393 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.3046. Min Act: -0.1700
Data Index: 8032257 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.2733. Min Act: -0.1700
Data Index: 6939160 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.2733. Min Act: -0.1700
Data Index: 4139123 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.2421. Min Act: -0.1700
Data Index: 6981392 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.2421. Min Act: -0.1700
Data Index: 2989512 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.2108. Min Act: -0.1700
Data Index: 1114643 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.2108. Min Act: -0.1700
Data Index: 4546734 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.1796. Min Act: -0.1700
Data Index: 7081976 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.1483. Min Act: -0.1700
Data Index: 3799842 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.1171. Min Act: -0.1700
Data Index: 3366270 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.1171. Min Act: -0.1700
Data Index: 4135067 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.0858. Min Act: -0.1700
Data Index: 4444787 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.0858. Min Act: -0.1700
Data Index: 4546735 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.0546. Min Act: -0.1700
Data Index: 1287875 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.0546. Min Act: -0.1700
Data Index: 2056301 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.0233. Min Act: -0.1700
Data Index: 5322472 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.0233. Min Act: -0.1700
Data Index: 8094338 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.0233. Min Act: -0.1700
Data Index: 7520951 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5233. Min Range: -5.5233
Max Act: 5.0233. Min Act: -0.1700
Data Index: 6357393 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19