Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0162. Min Range: -4.0162
Max Act: 4.0162. Min Act: -0.1700
Data Index: 5946236 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.7661. Min Act: -0.1700
Data Index: 1953364 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.7035. Min Act: -0.1700
Data Index: 1914766 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.7192. Min Act: -0.1700
Data Index: 8367397 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.7192. Min Act: -0.1700
Data Index: 4030896 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.7035. Min Act: -0.1700
Data Index: 5733669 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6879. Min Act: -0.1700
Data Index: 7436774 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6722. Min Act: -0.1700
Data Index: 3325066 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6566. Min Act: -0.1700
Data Index: 4248241 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6722. Min Act: -0.1700
Data Index: 5290493 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6409. Min Act: -0.1700
Data Index: 8654831 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6566. Min Act: -0.1700
Data Index: 1691773 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6409. Min Act: -0.1700
Data Index: 931463 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6096. Min Act: -0.1700
Data Index: 7381783 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6253. Min Act: -0.1700
Data Index: 8808067 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6253. Min Act: -0.1700
Data Index: 1267913 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6253. Min Act: -0.1700
Data Index: 1267912 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.6096. Min Act: -0.1700
Data Index: 5833652 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.5940. Min Act: -0.1700
Data Index: 2457072 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0162. Min Range: -4.0162
Max Act: 3.5940. Min Act: -0.1700
Data Index: 6292517 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19