Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 756 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1154. Min Range: -6.1154
Max Act: 6.1154. Min Act: -0.1700
Data Index: 4573491 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1154. Min Range: -6.1154
Max Act: 6.0216. Min Act: -0.1700
Data Index: 8810672 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.8654. Min Act: -0.1700
Data Index: 1258426 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.8654. Min Act: -0.1700
Data Index: 3928443 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.8654. Min Act: -0.1700
Data Index: 5022643 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.8341. Min Act: -0.1700
Data Index: 2336369 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.8029. Min Act: -0.1700
Data Index: 1707905 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.8029. Min Act: -0.1700
Data Index: 2113799 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.7716. Min Act: -0.1700
Data Index: 2360637 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.7404. Min Act: -0.1700
Data Index: 4229467 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.7091. Min Act: -0.1700
Data Index: 5211220 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.7091. Min Act: -0.1700
Data Index: 60276 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.7091. Min Act: -0.1700
Data Index: 6442540 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.6779. Min Act: -0.1700
Data Index: 1171379 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.6466. Min Act: -0.1700
Data Index: 8813206 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.6779. Min Act: -0.1700
Data Index: 7042846 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.6779. Min Act: -0.1700
Data Index: 7002898 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.6466. Min Act: -0.1700
Data Index: 6532322 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.6154. Min Act: -0.1700
Data Index: 6378219 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1154. Min Range: -6.1154
Max Act: 5.6466. Min Act: -0.1700
Data Index: 6843556 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19