Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5684. Min Range: -7.5684
Max Act: 7.5684. Min Act: -0.1700
Data Index: 8329006 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5684. Min Range: -7.5684
Max Act: 7.0996. Min Act: -0.1700
Data Index: 6804718 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5684. Min Range: -7.5684
Max Act: 7.0684. Min Act: -0.1700
Data Index: 8624155 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.7871. Min Act: -0.1700
Data Index: 4127565 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.7871. Min Act: -0.1700
Data Index: 1364458 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.7871. Min Act: -0.1700
Data Index: 4173818 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.7559. Min Act: -0.1700
Data Index: 2988866 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.6934. Min Act: -0.1700
Data Index: 5620503 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.6621. Min Act: -0.1700
Data Index: 3220980 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.5996. Min Act: -0.1700
Data Index: 1956733 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.5996. Min Act: -0.1700
Data Index: 6843041 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.6309. Min Act: -0.1700
Data Index: 6465672 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.5996. Min Act: -0.1700
Data Index: 5178627 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.6309. Min Act: -0.1700
Data Index: 108182 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.5684. Min Act: -0.1700
Data Index: 7537505 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.5684. Min Act: -0.1700
Data Index: 6582537 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.4746. Min Act: -0.1700
Data Index: 4911637 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.4434. Min Act: -0.1700
Data Index: 122256 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.4434. Min Act: -0.1700
Data Index: 203461 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5684. Min Range: -7.5684
Max Act: 6.4434. Min Act: -0.1700
Data Index: 6282557 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19