Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 706 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1368. Min Range: -7.1368
Max Act: 7.1368. Min Act: -0.1700
Data Index: 6923368 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1368. Min Range: -7.1368
Max Act: 7.0118. Min Act: -0.1700
Data Index: 2240398 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.8868. Min Act: -0.1700
Data Index: 557787 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.7618. Min Act: -0.1700
Data Index: 4576611 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.7618. Min Act: -0.1700
Data Index: 7393518 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.7618. Min Act: -0.1700
Data Index: 920533 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.7305. Min Act: -0.1700
Data Index: 7093690 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.7305. Min Act: -0.1700
Data Index: 5339332 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.6993. Min Act: -0.1700
Data Index: 8162800 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.6993. Min Act: -0.1700
Data Index: 7583391 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.6680. Min Act: -0.1700
Data Index: 1984332 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.6368. Min Act: -0.1700
Data Index: 330879 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.6368. Min Act: -0.1700
Data Index: 539954 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.6680. Min Act: -0.1700
Data Index: 4657808 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.5743. Min Act: -0.1700
Data Index: 6059968 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.5743. Min Act: -0.1700
Data Index: 3602890 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.5743. Min Act: -0.1700
Data Index: 7928113 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.5743. Min Act: -0.1700
Data Index: 4115684 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.4805. Min Act: -0.1700
Data Index: 6923360 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1368. Min Range: -7.1368
Max Act: 6.5118. Min Act: -0.1700
Data Index: 2793751 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19