Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.5798. Min Act: -0.1700
Data Index: 4252453 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.4860. Min Act: -0.1700
Data Index: 6784386 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.3610. Min Act: -0.1700
Data Index: 1158841 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.2985. Min Act: -0.1700
Data Index: 3660187 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.2985. Min Act: -0.1700
Data Index: 1088449 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.2985. Min Act: -0.1700
Data Index: 1352045 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.2673. Min Act: -0.1700
Data Index: 5673529 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.2360. Min Act: -0.1700
Data Index: 995641 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.2360. Min Act: -0.1700
Data Index: 1088444 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.2048. Min Act: -0.1700
Data Index: 3722515 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.1735. Min Act: -0.1700
Data Index: 2813718 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.2048. Min Act: -0.1700
Data Index: 6684653 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.2048. Min Act: -0.1700
Data Index: 3017994 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.1735. Min Act: -0.1700
Data Index: 558102 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.1735. Min Act: -0.1700
Data Index: 2347662 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.1735. Min Act: -0.1700
Data Index: 289011 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.1735. Min Act: -0.1700
Data Index: 3434530 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.1423. Min Act: -0.1700
Data Index: 1763016 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.1423. Min Act: -0.1700
Data Index: 5587917 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5798. Min Range: -5.5798
Max Act: 5.1110. Min Act: -0.1700
Data Index: 2257886 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19