Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3969 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1232. Min Range: -4.1232
Max Act: 4.1232. Min Act: -0.1700
Data Index: 8245159 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.9356. Min Act: -0.1700
Data Index: 2213665 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.8731. Min Act: -0.1700
Data Index: 7257164 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.8731. Min Act: -0.1700
Data Index: 8737223 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.8106. Min Act: -0.1700
Data Index: 6323999 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.8106. Min Act: -0.1700
Data Index: 3278276 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.8106. Min Act: -0.1700
Data Index: 3964780 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.8106. Min Act: -0.1700
Data Index: 6623772 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.7793. Min Act: -0.1700
Data Index: 3159934 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.7480. Min Act: -0.1700
Data Index: 1877994 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.7480. Min Act: -0.1700
Data Index: 86220 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.6854. Min Act: -0.1700
Data Index: 8737224 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.6854. Min Act: -0.1700
Data Index: 1766601 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.6854. Min Act: -0.1700
Data Index: 924664 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.6854. Min Act: -0.1700
Data Index: 4534291 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.6854. Min Act: -0.1700
Data Index: 7116801 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.6854. Min Act: -0.1700
Data Index: 3159929 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.6541. Min Act: -0.1700
Data Index: 221399 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.6541. Min Act: -0.1700
Data Index: 5598229 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1232. Min Range: -4.1232
Max Act: 3.6229. Min Act: -0.1700
Data Index: 5824574 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19