Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.2872. Min Act: -0.1700
Data Index: 8767725 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.1309. Min Act: -0.1700
Data Index: 4301215 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.1309. Min Act: -0.1700
Data Index: 3174037 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.1309. Min Act: -0.1700
Data Index: 2120569 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0996. Min Act: -0.1700
Data Index: 2850050 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0684. Min Act: -0.1700
Data Index: 4329626 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0684. Min Act: -0.1700
Data Index: 955258 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0371. Min Act: -0.1700
Data Index: 2014648 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0371. Min Act: -0.1700
Data Index: 1512615 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0371. Min Act: -0.1700
Data Index: 2251230 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0371. Min Act: -0.1700
Data Index: 1818368 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0371. Min Act: -0.1700
Data Index: 8401556 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0371. Min Act: -0.1700
Data Index: 5637710 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0371. Min Act: -0.1700
Data Index: 7658035 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0059. Min Act: -0.1700
Data Index: 4549648 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2872. Min Range: -4.2872
Max Act: 4.0059. Min Act: -0.1700
Data Index: 8172511 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2872. Min Range: -4.2872
Max Act: 3.9746. Min Act: -0.1700
Data Index: 7005568 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2872. Min Range: -4.2872
Max Act: 3.9746. Min Act: -0.1700
Data Index: 2935383 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2872. Min Range: -4.2872
Max Act: 3.9433. Min Act: -0.1700
Data Index: 1860779 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2872. Min Range: -4.2872
Max Act: 3.9433. Min Act: -0.1700
Data Index: 2271498 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19