Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1695 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.3272. Min Act: -0.1700
Data Index: 6087383 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.1709. Min Act: -0.1700
Data Index: 2443799 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.1709. Min Act: -0.1700
Data Index: 5958906 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3272. Min Range: -6.3272
Max Act: 6.1397. Min Act: -0.1700
Data Index: 456125 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.9834. Min Act: -0.1700
Data Index: 6392275 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.9834. Min Act: -0.1700
Data Index: 1658607 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.9522. Min Act: -0.1700
Data Index: 4517263 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.9522. Min Act: -0.1700
Data Index: 1898744 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.9209. Min Act: -0.1700
Data Index: 1517155 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.8897. Min Act: -0.1700
Data Index: 979126 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.8897. Min Act: -0.1700
Data Index: 5794933 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.8897. Min Act: -0.1700
Data Index: 7477338 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.8584. Min Act: -0.1700
Data Index: 5487773 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.8584. Min Act: -0.1700
Data Index: 8630551 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.8584. Min Act: -0.1700
Data Index: 6340904 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.8272. Min Act: -0.1700
Data Index: 8570320 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.7959. Min Act: -0.1700
Data Index: 1289500 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.7959. Min Act: -0.1700
Data Index: 8682770 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.7647. Min Act: -0.1700
Data Index: 3050714 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3272. Min Range: -6.3272
Max Act: 5.7647. Min Act: -0.1700
Data Index: 7344805 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19