Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.6922. Min Act: -0.1700
Data Index: 8219143 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.6610. Min Act: -0.1700
Data Index: 2372678 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.5985. Min Act: -0.1700
Data Index: 702337 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.5985. Min Act: -0.1700
Data Index: 5119869 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.5360. Min Act: -0.1700
Data Index: 4675803 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.5672. Min Act: -0.1700
Data Index: 4830072 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.5047. Min Act: -0.1700
Data Index: 1565268 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.5047. Min Act: -0.1700
Data Index: 4802210 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4735. Min Act: -0.1700
Data Index: 2168330 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.5047. Min Act: -0.1700
Data Index: 2189634 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4735. Min Act: -0.1700
Data Index: 6019845 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4735. Min Act: -0.1700
Data Index: 1722338 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4735. Min Act: -0.1700
Data Index: 557269 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4735. Min Act: -0.1700
Data Index: 4781170 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4735. Min Act: -0.1700
Data Index: 702342 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4110. Min Act: -0.1700
Data Index: 4057235 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4422. Min Act: -0.1700
Data Index: 6957330 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4110. Min Act: -0.1700
Data Index: 6188817 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4110. Min Act: -0.1700
Data Index: 2824850 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6922. Min Range: -5.6922
Max Act: 5.4422. Min Act: -0.1700
Data Index: 747931 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19