Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3742. Min Range: -7.3742
Max Act: 7.3742. Min Act: -0.1700
Data Index: 7643913 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3742. Min Range: -7.3742
Max Act: 7.2804. Min Act: -0.1700
Data Index: 1845640 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3742. Min Range: -7.3742
Max Act: 7.2492. Min Act: -0.1700
Data Index: 4591150 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3742. Min Range: -7.3742
Max Act: 7.1867. Min Act: -0.1700
Data Index: 149929 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3742. Min Range: -7.3742
Max Act: 7.1242. Min Act: -0.1700
Data Index: 2146864 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3742. Min Range: -7.3742
Max Act: 7.0617. Min Act: -0.1700
Data Index: 3815459 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3742. Min Range: -7.3742
Max Act: 7.0304. Min Act: -0.1700
Data Index: 8305635 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.9992. Min Act: -0.1700
Data Index: 6663051 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.9679. Min Act: -0.1700
Data Index: 2623819 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.9367. Min Act: -0.1700
Data Index: 5780302 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.9367. Min Act: -0.1700
Data Index: 2788199 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.9054. Min Act: -0.1700
Data Index: 280588 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.9054. Min Act: -0.1700
Data Index: 6299048 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.9054. Min Act: -0.1700
Data Index: 1124669 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.9054. Min Act: -0.1700
Data Index: 3433830 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.9054. Min Act: -0.1700
Data Index: 2285988 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.8742. Min Act: -0.1700
Data Index: 841880 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.8742. Min Act: -0.1700
Data Index: 4719951 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.8742. Min Act: -0.1700
Data Index: 4090633 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3742. Min Range: -7.3742
Max Act: 6.8742. Min Act: -0.1700
Data Index: 6335067 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19