Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5825. Min Act: -0.1700
Data Index: 3157260 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5825. Min Act: -0.1700
Data Index: 4761389 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5513. Min Act: -0.1700
Data Index: 3080917 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5513. Min Act: -0.1700
Data Index: 511417 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5200. Min Act: -0.1700
Data Index: 3879827 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5513. Min Act: -0.1700
Data Index: 1027521 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5200. Min Act: -0.1700
Data Index: 3165680 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5513. Min Act: -0.1700
Data Index: 3894571 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5200. Min Act: -0.1700
Data Index: 4102861 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5513. Min Act: -0.1700
Data Index: 6222484 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5513. Min Act: -0.1700
Data Index: 5320324 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5200. Min Act: -0.1700
Data Index: 3724747 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.4888. Min Act: -0.1700
Data Index: 3133243 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5200. Min Act: -0.1700
Data Index: 6309774 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5200. Min Act: -0.1700
Data Index: 4452778 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5513. Min Act: -0.1700
Data Index: 2183300 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5200. Min Act: -0.1700
Data Index: 4222471 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5200. Min Act: -0.1700
Data Index: 1140695 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5200. Min Act: -0.1700
Data Index: 1015946 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5825. Min Range: -4.5825
Max Act: 4.5200. Min Act: -0.1700
Data Index: 2919973 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19