Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1879. Min Range: -6.1879
Max Act: 6.1879. Min Act: -0.1700
Data Index: 7841179 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1879. Min Range: -6.1879
Max Act: 6.1567. Min Act: -0.1700
Data Index: 1626429 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1879. Min Range: -6.1879
Max Act: 6.1567. Min Act: -0.1700
Data Index: 7841178 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1879. Min Range: -6.1879
Max Act: 6.0004. Min Act: -0.1700
Data Index: 3773919 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1879. Min Range: -6.1879
Max Act: 6.0004. Min Act: -0.1700
Data Index: 3163269 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.9692. Min Act: -0.1700
Data Index: 3348067 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.9379. Min Act: -0.1700
Data Index: 7841175 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.9067. Min Act: -0.1700
Data Index: 7214916 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.9067. Min Act: -0.1700
Data Index: 2851178 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.8754. Min Act: -0.1700
Data Index: 7688589 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.8442. Min Act: -0.1700
Data Index: 4459375 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.8442. Min Act: -0.1700
Data Index: 7841177 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.8442. Min Act: -0.1700
Data Index: 7868421 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.8129. Min Act: -0.1700
Data Index: 4480362 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.7817. Min Act: -0.1700
Data Index: 2420723 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.7504. Min Act: -0.1700
Data Index: 6399377 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.7192. Min Act: -0.1700
Data Index: 7841176 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.7192. Min Act: -0.1700
Data Index: 3218214 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.7192. Min Act: -0.1700
Data Index: 6360364 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1879. Min Range: -6.1879
Max Act: 5.7192. Min Act: -0.1700
Data Index: 3485059 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19