Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4264 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.5610. Min Act: -0.1700
Data Index: 135162 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.5610. Min Act: -0.1700
Data Index: 3439852 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.5297. Min Act: -0.1700
Data Index: 2008994 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4672. Min Act: -0.1700
Data Index: 5068918 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4985. Min Act: -0.1700
Data Index: 6933742 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4985. Min Act: -0.1700
Data Index: 8103200 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4672. Min Act: -0.1700
Data Index: 3009017 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4360. Min Act: -0.1700
Data Index: 151579 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4360. Min Act: -0.1700
Data Index: 1999487 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4047. Min Act: -0.1700
Data Index: 4487021 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4047. Min Act: -0.1700
Data Index: 3878227 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4047. Min Act: -0.1700
Data Index: 8621166 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.3422. Min Act: -0.1700
Data Index: 7071904 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.3422. Min Act: -0.1700
Data Index: 2841757 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.3110. Min Act: -0.1700
Data Index: 1792770 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.3110. Min Act: -0.1700
Data Index: 450145 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.3110. Min Act: -0.1700
Data Index: 8283842 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.3110. Min Act: -0.1700
Data Index: 2249754 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.3110. Min Act: -0.1700
Data Index: 4147215 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.2485. Min Act: -0.1700
Data Index: 8459647 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19