Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.6574. Min Act: -0.1700
Data Index: 2798399 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.6574. Min Act: -0.1700
Data Index: 5201118 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.6261. Min Act: -0.1700
Data Index: 5692359 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.5011. Min Act: -0.1700
Data Index: 3733667 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.4699. Min Act: -0.1700
Data Index: 442470 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.4699. Min Act: -0.1700
Data Index: 1033552 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.4386. Min Act: -0.1697
Data Index: 3311363 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.4386. Min Act: -0.1700
Data Index: 2604592 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.4074. Min Act: -0.1700
Data Index: 3099781 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.4074. Min Act: -0.1700
Data Index: 7701474 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.4074. Min Act: -0.1700
Data Index: 7207049 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.4074. Min Act: -0.1700
Data Index: 4851793 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.4074. Min Act: -0.1699
Data Index: 1729932 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.4074. Min Act: -0.1685
Data Index: 3311365 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.3761. Min Act: -0.1700
Data Index: 5975704 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.3761. Min Act: -0.1698
Data Index: 4607323 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.3761. Min Act: -0.1698
Data Index: 4940919 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.3761. Min Act: -0.1700
Data Index: 5151626 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.3761. Min Act: -0.1700
Data Index: 5964914 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6574. Min Range: -4.6574
Max Act: 4.3761. Min Act: -0.1700
Data Index: 5153379 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19