Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1577. Min Range: -5.1577
Max Act: 5.1577. Min Act: -0.1700
Data Index: 7258449 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1577. Min Range: -5.1577
Max Act: 5.1265. Min Act: -0.1700
Data Index: 3085973 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1577. Min Range: -5.1577
Max Act: 5.0327. Min Act: -0.1700
Data Index: 4202729 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.9077. Min Act: -0.1700
Data Index: 6124536 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.8765. Min Act: -0.1700
Data Index: 3878489 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.8452. Min Act: -0.1700
Data Index: 7954785 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.8452. Min Act: -0.1700
Data Index: 1086708 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.8140. Min Act: -0.1700
Data Index: 8708145 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.7827. Min Act: -0.1700
Data Index: 5969902 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.7827. Min Act: -0.1700
Data Index: 3907455 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.7515. Min Act: -0.1700
Data Index: 4920266 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.7202. Min Act: -0.1700
Data Index: 6089329 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.6890. Min Act: -0.1700
Data Index: 384800 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.7202. Min Act: -0.1700
Data Index: 2841923 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.6890. Min Act: -0.1700
Data Index: 7027853 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.6890. Min Act: -0.1700
Data Index: 1278401 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.6890. Min Act: -0.1700
Data Index: 8810 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.6890. Min Act: -0.1700
Data Index: 1242770 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.6890. Min Act: -0.1700
Data Index: 3170779 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1577. Min Range: -5.1577
Max Act: 4.6890. Min Act: -0.1700
Data Index: 740293 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19