Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.3571. Min Act: -0.1700
Data Index: 8102478 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.2946. Min Act: -0.1700
Data Index: 1924838 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.2321. Min Act: -0.1700
Data Index: 3529872 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.1696. Min Act: -0.1700
Data Index: 4772930 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.1696. Min Act: -0.1700
Data Index: 8360 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.1384. Min Act: -0.1700
Data Index: 6298427 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.1071. Min Act: -0.1700
Data Index: 6775859 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.0446. Min Act: -0.1700
Data Index: 264868 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.0759. Min Act: -0.1700
Data Index: 2441331 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.0759. Min Act: -0.1700
Data Index: 1997614 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.0446. Min Act: -0.1700
Data Index: 8289093 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.0759. Min Act: -0.1700
Data Index: 1118539 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.0759. Min Act: -0.1700
Data Index: 1126110 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.0759. Min Act: -0.1700
Data Index: 6860508 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.0446. Min Act: -0.1700
Data Index: 7541148 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.0134. Min Act: -0.1700
Data Index: 4596489 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3571. Min Range: -7.3571
Max Act: 7.0134. Min Act: -0.1700
Data Index: 4894636 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3571. Min Range: -7.3571
Max Act: 6.9821. Min Act: -0.1700
Data Index: 483643 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3571. Min Range: -7.3571
Max Act: 6.9821. Min Act: -0.1700
Data Index: 4484227 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3571. Min Range: -7.3571
Max Act: 6.9821. Min Act: -0.1700
Data Index: 3390667 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19