Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1534. Min Range: -9.1534
Max Act: 9.1534. Min Act: -0.1700
Data Index: 4637555 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1534. Min Range: -9.1534
Max Act: 9.0284. Min Act: -0.1700
Data Index: 6354591 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1534. Min Range: -9.1534
Max Act: 9.0284. Min Act: -0.1700
Data Index: 5030454 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.7784. Min Act: -0.1700
Data Index: 5708614 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.7159. Min Act: -0.1700
Data Index: 5520917 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.5909. Min Act: -0.1700
Data Index: 4675345 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.5284. Min Act: -0.1700
Data Index: 7760001 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.4659. Min Act: -0.1700
Data Index: 6242251 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.3409. Min Act: -0.1700
Data Index: 982067 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.3409. Min Act: -0.1700
Data Index: 4925475 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.2784. Min Act: -0.1700
Data Index: 1391265 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.2784. Min Act: -0.1700
Data Index: 5605920 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.2784. Min Act: -0.1700
Data Index: 2467228 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.2784. Min Act: -0.1700
Data Index: 1815191 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.2784. Min Act: -0.1700
Data Index: 6577818 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.3409. Min Act: -0.1700
Data Index: 4384168 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.2159. Min Act: -0.1700
Data Index: 3991244 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.2159. Min Act: -0.1700
Data Index: 1443993 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.2159. Min Act: -0.1700
Data Index: 3512362 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1534. Min Range: -9.1534
Max Act: 8.2784. Min Act: -0.1700
Data Index: 7351385 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19