Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.5805. Min Act: -0.1700
Data Index: 6133055 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.6117. Min Act: -0.1700
Data Index: 2114074 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.4867. Min Act: -0.1700
Data Index: 3266870 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.4867. Min Act: -0.1700
Data Index: 3102181 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.3930. Min Act: -0.1700
Data Index: 8179301 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.3617. Min Act: -0.1700
Data Index: 1178239 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.3617. Min Act: -0.1700
Data Index: 6341943 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.3305. Min Act: -0.1700
Data Index: 3210653 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.2367. Min Act: -0.1700
Data Index: 3175981 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.2367. Min Act: -0.1700
Data Index: 4790428 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.2055. Min Act: -0.1700
Data Index: 2534160 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.2367. Min Act: -0.1700
Data Index: 3833450 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.2055. Min Act: -0.1700
Data Index: 5181033 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.1430. Min Act: -0.1700
Data Index: 8418812 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.2055. Min Act: -0.1700
Data Index: 4570431 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.1742. Min Act: -0.1700
Data Index: 7391294 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.1430. Min Act: -0.1700
Data Index: 5216472 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.1742. Min Act: -0.1700
Data Index: 6343634 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.1430. Min Act: -0.1700
Data Index: 6824938 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6117. Min Range: -4.6117
Max Act: 4.0804. Min Act: -0.1700
Data Index: 901628 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19