Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1167 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.6046. Min Act: -0.1700
Data Index: 1773841 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.5885. Min Act: -0.1700
Data Index: 7614854 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.5724. Min Act: -0.1700
Data Index: 535523 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.5724. Min Act: -0.1700
Data Index: 3697745 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.5402. Min Act: -0.1700
Data Index: 5092602 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.5078. Min Act: -0.1700
Data Index: 5590434 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4916. Min Act: -0.1700
Data Index: 426557 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.5078. Min Act: -0.1700
Data Index: 3812457 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4916. Min Act: -0.1700
Data Index: 70957 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4754. Min Act: -0.1699
Data Index: 8362135 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.5078. Min Act: -0.1700
Data Index: 6979162 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4754. Min Act: -0.1700
Data Index: 4078447 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4754. Min Act: -0.1700
Data Index: 7355485 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4591. Min Act: -0.1700
Data Index: 1069626 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4591. Min Act: -0.1700
Data Index: 435562 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4429. Min Act: -0.1700
Data Index: 7995150 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4591. Min Act: -0.1700
Data Index: 1264344 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4591. Min Act: -0.1700
Data Index: 3128592 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4591. Min Act: -0.1700
Data Index: 919178 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6046. Min Range: -2.6046
Max Act: 2.4429. Min Act: -0.1700
Data Index: 4804673 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19