Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3330 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.6782. Min Range: -17.6782
Max Act: 17.6782. Min Act: -0.1700
Data Index: 5981986 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.6782. Min Range: -17.6782
Max Act: 17.6782. Min Act: -0.1700
Data Index: 2869951 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.6782. Min Range: -17.6782
Max Act: 17.5532. Min Act: -0.1700
Data Index: 7058132 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.6782. Min Range: -17.6782
Max Act: 17.5532. Min Act: -0.1700
Data Index: 426904 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.6782. Min Range: -17.6782
Max Act: 17.5532. Min Act: -0.1700
Data Index: 4703624 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.6782. Min Range: -17.6782
Max Act: 17.3032. Min Act: -0.1700
Data Index: 7647336 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.6782. Min Range: -17.6782
Max Act: 17.0532. Min Act: -0.1700
Data Index: 953391 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.6782. Min Range: -17.6782
Max Act: 17.0532. Min Act: -0.1700
Data Index: 3656319 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.9282. Min Act: -0.1700
Data Index: 7017497 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.9282. Min Act: -0.1700
Data Index: 5986594 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.9282. Min Act: -0.1700
Data Index: 953377 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.8032. Min Act: -0.1700
Data Index: 1988512 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.6782. Min Act: -0.1700
Data Index: 3012103 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.5532. Min Act: -0.1700
Data Index: 4304081 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.5532. Min Act: -0.1700
Data Index: 8462643 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.5532. Min Act: -0.1700
Data Index: 1819166 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.4282. Min Act: -0.1700
Data Index: 4304080 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.4282. Min Act: -0.1700
Data Index: 4188257 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.4282. Min Act: -0.1700
Data Index: 6405237 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.6782. Min Range: -17.6782
Max Act: 16.4282. Min Act: -0.1700
Data Index: 4726438 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19