Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.9375. Min Act: -0.1700
Data Index: 3786561 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.8437. Min Act: -0.1700
Data Index: 418774 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.7812. Min Act: -0.1700
Data Index: 176890 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.8125. Min Act: -0.1700
Data Index: 5667679 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.7500. Min Act: -0.1700
Data Index: 3383926 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.7812. Min Act: -0.1700
Data Index: 1467471 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.7812. Min Act: -0.1700
Data Index: 1583084 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.7812. Min Act: -0.1700
Data Index: 608417 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.7812. Min Act: -0.1700
Data Index: 2991799 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.7500. Min Act: -0.1700
Data Index: 4055475 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.7187. Min Act: -0.1700
Data Index: 87444 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.7187. Min Act: -0.1700
Data Index: 8118585 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.6875. Min Act: -0.1700
Data Index: 7356577 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.6875. Min Act: -0.1700
Data Index: 8773328 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.6875. Min Act: -0.1700
Data Index: 549585 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.6562. Min Act: -0.1700
Data Index: 2123455 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.6562. Min Act: -0.1700
Data Index: 335477 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.6562. Min Act: -0.1700
Data Index: 6188983 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.6562. Min Act: -0.1700
Data Index: 673920 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9375. Min Range: -4.9375
Max Act: 4.5937. Min Act: -0.1700
Data Index: 3425228 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19