Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.9783. Min Range: -10.9783
Max Act: 10.9783. Min Act: -0.1700
Data Index: 8354094 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9783. Min Range: -10.9783
Max Act: 10.6033. Min Act: -0.1700
Data Index: 2350592 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9783. Min Range: -10.9783
Max Act: 10.4158. Min Act: -0.1700
Data Index: 4086293 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9783. Min Range: -10.9783
Max Act: 10.4158. Min Act: -0.1700
Data Index: 4344369 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9783. Min Range: -10.9783
Max Act: 10.3533. Min Act: -0.1700
Data Index: 5369420 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9783. Min Range: -10.9783
Max Act: 10.2908. Min Act: -0.1700
Data Index: 4695431 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9783. Min Range: -10.9783
Max Act: 10.1033. Min Act: -0.1700
Data Index: 3688690 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.9783. Min Act: -0.1700
Data Index: 6063531 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9783. Min Range: -10.9783
Max Act: 10.0408. Min Act: -0.1700
Data Index: 4377177 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.9158. Min Act: -0.1700
Data Index: 5930815 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.7908. Min Act: -0.1700
Data Index: 1767397 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.8533. Min Act: -0.1693
Data Index: 1846236 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.8533. Min Act: -0.1700
Data Index: 8692058 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.8533. Min Act: -0.1700
Data Index: 2023025 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.7908. Min Act: -0.1700
Data Index: 8227891 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.7908. Min Act: -0.1700
Data Index: 1267682 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.7908. Min Act: -0.1700
Data Index: 1123304 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.7283. Min Act: -0.1700
Data Index: 2992021 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.6033. Min Act: -0.1700
Data Index: 7884496 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9783. Min Range: -10.9783
Max Act: 9.6033. Min Act: -0.1700
Data Index: 1598756 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19