Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.9118. Min Act: -0.1700
Data Index: 8272078 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.6930. Min Act: -0.1700
Data Index: 5109065 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.6618. Min Act: -0.1700
Data Index: 8487083 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.6618. Min Act: -0.1700
Data Index: 2802663 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.6618. Min Act: -0.1700
Data Index: 7680983 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.6618. Min Act: -0.1700
Data Index: 8807510 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.6618. Min Act: -0.1700
Data Index: 5470007 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.6618. Min Act: -0.1700
Data Index: 5554474 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.6305. Min Act: -0.1700
Data Index: 6477501 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.5993. Min Act: -0.1700
Data Index: 7831317 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.5680. Min Act: -0.1700
Data Index: 96450 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.5680. Min Act: -0.1700
Data Index: 6955228 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.5680. Min Act: -0.1700
Data Index: 2054104 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.5368. Min Act: -0.1700
Data Index: 6078599 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.5055. Min Act: -0.1700
Data Index: 8594632 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.5368. Min Act: -0.1700
Data Index: 7777179 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.5368. Min Act: -0.1700
Data Index: 4352054 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.5055. Min Act: -0.1700
Data Index: 6549971 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.4743. Min Act: -0.1700
Data Index: 4481016 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9118. Min Range: -5.9118
Max Act: 5.4430. Min Act: -0.1700
Data Index: 6007299 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19