Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2386 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1155. Min Range: -7.1155
Max Act: 7.1155. Min Act: -0.1700
Data Index: 4942463 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1155. Min Range: -7.1155
Max Act: 7.0843. Min Act: -0.1700
Data Index: 1500605 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1155. Min Range: -7.1155
Max Act: 7.0843. Min Act: -0.1700
Data Index: 5058919 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.9905. Min Act: -0.1700
Data Index: 3458052 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.9593. Min Act: -0.1700
Data Index: 4138366 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.7718. Min Act: -0.1700
Data Index: 2894025 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.8030. Min Act: -0.1700
Data Index: 2288425 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.7093. Min Act: -0.1700
Data Index: 1630886 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.6780. Min Act: -0.1700
Data Index: 8051190 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.6468. Min Act: -0.1700
Data Index: 1856057 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.6155. Min Act: -0.1700
Data Index: 6661711 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.6155. Min Act: -0.1700
Data Index: 619041 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.5843. Min Act: -0.1700
Data Index: 7500888 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.5843. Min Act: -0.1700
Data Index: 702899 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.5843. Min Act: -0.1700
Data Index: 3105797 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.5843. Min Act: -0.1700
Data Index: 5039246 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.5530. Min Act: -0.1700
Data Index: 5692003 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.5843. Min Act: -0.1700
Data Index: 5024602 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.5530. Min Act: -0.1700
Data Index: 5369930 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1155. Min Range: -7.1155
Max Act: 6.4905. Min Act: -0.1700
Data Index: 766090 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19