Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3155 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3013. Min Range: -8.3013
Max Act: 8.3013. Min Act: -0.1700
Data Index: 7093698 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3013. Min Range: -8.3013
Max Act: 8.2388. Min Act: -0.1700
Data Index: 7579700 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3013. Min Range: -8.3013
Max Act: 8.2388. Min Act: -0.1700
Data Index: 3943522 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3013. Min Range: -8.3013
Max Act: 8.1763. Min Act: -0.1700
Data Index: 3281031 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3013. Min Range: -8.3013
Max Act: 8.1138. Min Act: -0.1700
Data Index: 6616784 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3013. Min Range: -8.3013
Max Act: 8.0513. Min Act: -0.1700
Data Index: 5394234 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3013. Min Range: -8.3013
Max Act: 8.1138. Min Act: -0.1700
Data Index: 3943512 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3013. Min Range: -8.3013
Max Act: 8.0513. Min Act: -0.1700
Data Index: 275875 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3013. Min Range: -8.3013
Max Act: 8.0513. Min Act: -0.1700
Data Index: 4214159 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3013. Min Range: -8.3013
Max Act: 8.1138. Min Act: -0.1700
Data Index: 6431758 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3013. Min Range: -8.3013
Max Act: 7.9888. Min Act: -0.1700
Data Index: 1428337 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3013. Min Range: -8.3013
Max Act: 7.9888. Min Act: -0.1700
Data Index: 7163731 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3013. Min Range: -8.3013
Max Act: 7.9888. Min Act: -0.1700
Data Index: 6637417 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3013. Min Range: -8.3013
Max Act: 7.9888. Min Act: -0.1700
Data Index: 4434908 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3013. Min Range: -8.3013
Max Act: 7.9888. Min Act: -0.1700
Data Index: 6173660 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3013. Min Range: -8.3013
Max Act: 7.9888. Min Act: -0.1700
Data Index: 4155973 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3013. Min Range: -8.3013
Max Act: 7.9888. Min Act: -0.1700
Data Index: 2325643 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3013. Min Range: -8.3013
Max Act: 7.9888. Min Act: -0.1700
Data Index: 4076226 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3013. Min Range: -8.3013
Max Act: 7.9888. Min Act: -0.1700
Data Index: 1544676 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3013. Min Range: -8.3013
Max Act: 7.9888. Min Act: -0.1700
Data Index: 1106979 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19