Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5098. Min Range: -7.5098
Max Act: 7.5098. Min Act: -0.1700
Data Index: 783015 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5098. Min Range: -7.5098
Max Act: 7.3223. Min Act: -0.1700
Data Index: 757350 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5098. Min Range: -7.5098
Max Act: 7.0723. Min Act: -0.1700
Data Index: 4722793 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5098. Min Range: -7.5098
Max Act: 7.0723. Min Act: -0.1700
Data Index: 5922094 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.9160. Min Act: -0.1700
Data Index: 5474401 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5098. Min Range: -7.5098
Max Act: 7.0410. Min Act: -0.1700
Data Index: 5516332 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.9785. Min Act: -0.1700
Data Index: 2303935 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.9473. Min Act: -0.1700
Data Index: 2303956 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.8848. Min Act: -0.1700
Data Index: 8476152 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.8848. Min Act: -0.1700
Data Index: 1195242 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.8848. Min Act: -0.1700
Data Index: 2303960 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.9160. Min Act: -0.1700
Data Index: 2303962 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.8223. Min Act: -0.1700
Data Index: 4722802 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.7910. Min Act: -0.1700
Data Index: 4722823 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.7285. Min Act: -0.1700
Data Index: 2303959 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.7285. Min Act: -0.1700
Data Index: 6380052 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.7910. Min Act: -0.1700
Data Index: 2303954 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.7910. Min Act: -0.1700
Data Index: 5926536 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.7910. Min Act: -0.1700
Data Index: 2303949 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5098. Min Range: -7.5098
Max Act: 6.7598. Min Act: -0.1700
Data Index: 5504011 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19