Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5500 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1873. Min Range: -6.1873
Max Act: 6.1873. Min Act: -0.1700
Data Index: 5484063 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1873. Min Range: -6.1873
Max Act: 6.0311. Min Act: -0.1700
Data Index: 5484064 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.8748. Min Act: -0.1700
Data Index: 1887793 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.8748. Min Act: -0.1700
Data Index: 2930189 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.8436. Min Act: -0.1700
Data Index: 2705426 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.8123. Min Act: -0.1700
Data Index: 3480077 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.7498. Min Act: -0.1700
Data Index: 8188690 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.7186. Min Act: -0.1700
Data Index: 7335252 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.7186. Min Act: -0.1700
Data Index: 1463773 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6561. Min Act: -0.1700
Data Index: 664727 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6873. Min Act: -0.1700
Data Index: 2764757 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6873. Min Act: -0.1700
Data Index: 6525377 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6873. Min Act: -0.1700
Data Index: 8538669 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6561. Min Act: -0.1700
Data Index: 8613876 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6561. Min Act: -0.1700
Data Index: 145121 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6561. Min Act: -0.1700
Data Index: 8663220 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6248. Min Act: -0.1700
Data Index: 5686575 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6561. Min Act: -0.1700
Data Index: 4700864 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6873. Min Act: -0.1700
Data Index: 6221199 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1873. Min Range: -6.1873
Max Act: 5.6561. Min Act: -0.1700
Data Index: 851755 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19