Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.8690. Min Act: -0.1700
Data Index: 4377561 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.8378. Min Act: -0.1700
Data Index: 6762837 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.7753. Min Act: -0.1700
Data Index: 7401399 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.7440. Min Act: -0.1700
Data Index: 245805 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.7440. Min Act: -0.1700
Data Index: 8570663 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.7440. Min Act: -0.1700
Data Index: 4511948 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6815. Min Act: -0.1700
Data Index: 1695064 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6815. Min Act: -0.1700
Data Index: 7513361 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6503. Min Act: -0.1700
Data Index: 1437701 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6815. Min Act: -0.1700
Data Index: 6960896 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6503. Min Act: -0.1700
Data Index: 8716538 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6503. Min Act: -0.1700
Data Index: 6068471 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6503. Min Act: -0.1700
Data Index: 1981207 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6503. Min Act: -0.1700
Data Index: 5476374 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6503. Min Act: -0.1700
Data Index: 8718913 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6190. Min Act: -0.1700
Data Index: 3221478 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6190. Min Act: -0.1700
Data Index: 8377385 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6190. Min Act: -0.1700
Data Index: 1440126 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.6503. Min Act: -0.1700
Data Index: 3458990 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5878. Min Act: -0.1700
Data Index: 8548509 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19