Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1929. Min Range: -8.1929
Max Act: 8.1929. Min Act: -0.1700
Data Index: 4545066 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.8804. Min Act: -0.1700
Data Index: 6338770 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.8179. Min Act: -0.1700
Data Index: 7277166 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.7554. Min Act: -0.1700
Data Index: 3579591 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.6929. Min Act: -0.1700
Data Index: 4266137 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.6304. Min Act: -0.1700
Data Index: 1528988 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.6304. Min Act: -0.1700
Data Index: 1183821 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.6304. Min Act: -0.1700
Data Index: 1125746 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.6304. Min Act: -0.1700
Data Index: 2540468 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.6304. Min Act: -0.1700
Data Index: 8389537 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.5679. Min Act: -0.1700
Data Index: 828087 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.5679. Min Act: -0.1700
Data Index: 8412331 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.5054. Min Act: -0.1700
Data Index: 3660434 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.5679. Min Act: -0.1700
Data Index: 8808884 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.5054. Min Act: -0.1700
Data Index: 6559579 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.5054. Min Act: -0.1700
Data Index: 3078589 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.5054. Min Act: -0.1700
Data Index: 554131 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.5054. Min Act: -0.1700
Data Index: 2851456 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.5054. Min Act: -0.1700
Data Index: 5483954 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1929. Min Range: -8.1929
Max Act: 7.4429. Min Act: -0.1700
Data Index: 3154872 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19