Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2697 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.8584. Min Act: -0.1700
Data Index: 1022589 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.8584. Min Act: -0.1700
Data Index: 2104707 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.6084. Min Act: -0.1700
Data Index: 701507 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.6709. Min Act: -0.1700
Data Index: 4818949 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.6709. Min Act: -0.1700
Data Index: 324374 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.5771. Min Act: -0.1700
Data Index: 8425271 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.3896. Min Act: -0.1700
Data Index: 3317840 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.3896. Min Act: -0.1700
Data Index: 2100037 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.3584. Min Act: -0.1700
Data Index: 8744229 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.2646. Min Act: -0.1700
Data Index: 1788821 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.2646. Min Act: -0.1700
Data Index: 634528 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.2646. Min Act: -0.1700
Data Index: 7268431 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.2334. Min Act: -0.1700
Data Index: 3571355 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.2021. Min Act: -0.1700
Data Index: 7148299 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.2021. Min Act: -0.1700
Data Index: 4644170 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.2021. Min Act: -0.1700
Data Index: 1808861 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.1709. Min Act: -0.1700
Data Index: 1817285 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.1709. Min Act: -0.1700
Data Index: 7270964 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.1396. Min Act: -0.1700
Data Index: 5814996 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8584. Min Range: -7.8584
Max Act: 7.1084. Min Act: -0.1700
Data Index: 8052094 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19