Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4916 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.5059. Min Act: -0.1700
Data Index: 3862581 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.5059. Min Act: -0.1700
Data Index: 606566 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.4746. Min Act: -0.1700
Data Index: 6095597 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.4434. Min Act: -0.1700
Data Index: 7742021 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.4121. Min Act: -0.1700
Data Index: 5624860 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.4121. Min Act: -0.1700
Data Index: 6770791 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3496. Min Act: -0.1700
Data Index: 7369520 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3809. Min Act: -0.1700
Data Index: 6269322 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3496. Min Act: -0.1700
Data Index: 877067 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3184. Min Act: -0.1700
Data Index: 7659414 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3496. Min Act: -0.1700
Data Index: 1213128 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2871. Min Act: -0.1700
Data Index: 1208832 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.3184. Min Act: -0.1700
Data Index: 3413673 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2871. Min Act: -0.1700
Data Index: 6942890 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2871. Min Act: -0.1700
Data Index: 4801688 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2871. Min Act: -0.1700
Data Index: 8065082 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2871. Min Act: -0.1700
Data Index: 7892652 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2871. Min Act: -0.1700
Data Index: 4778767 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2559. Min Act: -0.1700
Data Index: 1273721 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5059. Min Range: -4.5059
Max Act: 4.2559. Min Act: -0.1700
Data Index: 7300308 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19