Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1134. Min Range: -7.1134
Max Act: 7.1134. Min Act: -0.1700
Data Index: 1350377 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.8634. Min Act: -0.1700
Data Index: 3896507 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.8634. Min Act: -0.1700
Data Index: 365349 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.7696. Min Act: -0.1700
Data Index: 2020760 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.7696. Min Act: -0.1700
Data Index: 6578010 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.7384. Min Act: -0.1700
Data Index: 1425284 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.7071. Min Act: -0.1700
Data Index: 8440807 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.6446. Min Act: -0.1700
Data Index: 6260466 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.6446. Min Act: -0.1700
Data Index: 412486 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.6134. Min Act: -0.1700
Data Index: 4647971 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.6134. Min Act: -0.1700
Data Index: 5617079 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.6134. Min Act: -0.1700
Data Index: 6860385 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.5821. Min Act: -0.1700
Data Index: 5150957 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.5509. Min Act: -0.1700
Data Index: 3900097 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.5196. Min Act: -0.1700
Data Index: 4580507 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.5196. Min Act: -0.1700
Data Index: 2772896 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.5509. Min Act: -0.1700
Data Index: 2198641 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.5196. Min Act: -0.1700
Data Index: 2109731 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.5196. Min Act: -0.1700
Data Index: 2170425 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1134. Min Range: -7.1134
Max Act: 6.5196. Min Act: -0.1700
Data Index: 8411230 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19