Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 346 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4702. Min Range: -7.4702
Max Act: 7.4702. Min Act: -0.1700
Data Index: 986208 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4702. Min Range: -7.4702
Max Act: 7.1577. Min Act: -0.1700
Data Index: 7610892 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4702. Min Range: -7.4702
Max Act: 7.0327. Min Act: -0.1700
Data Index: 6728728 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4702. Min Range: -7.4702
Max Act: 7.0327. Min Act: -0.1700
Data Index: 3332982 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4702. Min Range: -7.4702
Max Act: 7.0327. Min Act: -0.1700
Data Index: 4880269 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4702. Min Range: -7.4702
Max Act: 7.0014. Min Act: -0.1700
Data Index: 8166858 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.9389. Min Act: -0.1700
Data Index: 3377938 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.8764. Min Act: -0.1700
Data Index: 2273936 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.8764. Min Act: -0.1700
Data Index: 2830636 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.8452. Min Act: -0.1700
Data Index: 5782866 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.8452. Min Act: -0.1700
Data Index: 2107447 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.8139. Min Act: -0.1700
Data Index: 5683825 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.8452. Min Act: -0.1700
Data Index: 2023234 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.7827. Min Act: -0.1700
Data Index: 1840238 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.7827. Min Act: -0.1700
Data Index: 733507 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.7514. Min Act: -0.1700
Data Index: 3638193 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.7202. Min Act: -0.1700
Data Index: 5982588 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.6889. Min Act: -0.1700
Data Index: 3450029 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.6264. Min Act: -0.1700
Data Index: 4288673 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4702. Min Range: -7.4702
Max Act: 6.6889. Min Act: -0.1700
Data Index: 2351948 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19