Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5953. Min Range: -7.5953
Max Act: 7.5953. Min Act: -0.1700
Data Index: 366739 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5953. Min Range: -7.5953
Max Act: 7.3453. Min Act: -0.1700
Data Index: 519843 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5953. Min Range: -7.5953
Max Act: 7.2516. Min Act: -0.1700
Data Index: 6856990 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5953. Min Range: -7.5953
Max Act: 7.2516. Min Act: -0.1700
Data Index: 2785237 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5953. Min Range: -7.5953
Max Act: 7.2516. Min Act: -0.1700
Data Index: 789806 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5953. Min Range: -7.5953
Max Act: 7.1578. Min Act: -0.1700
Data Index: 7249954 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5953. Min Range: -7.5953
Max Act: 7.0953. Min Act: -0.1700
Data Index: 4839092 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5953. Min Range: -7.5953
Max Act: 7.0641. Min Act: -0.1700
Data Index: 4784693 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5953. Min Range: -7.5953
Max Act: 7.0953. Min Act: -0.1700
Data Index: 1582887 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5953. Min Range: -7.5953
Max Act: 7.0016. Min Act: -0.1700
Data Index: 3364343 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5953. Min Range: -7.5953
Max Act: 6.9703. Min Act: -0.1700
Data Index: 1699611 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5953. Min Range: -7.5953
Max Act: 6.9703. Min Act: -0.1700
Data Index: 3782924 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5953. Min Range: -7.5953
Max Act: 6.9703. Min Act: -0.1700
Data Index: 2826683 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5953. Min Range: -7.5953
Max Act: 6.9078. Min Act: -0.1700
Data Index: 5229623 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5953. Min Range: -7.5953
Max Act: 6.8766. Min Act: -0.1700
Data Index: 2864288 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5953. Min Range: -7.5953
Max Act: 6.9078. Min Act: -0.1700
Data Index: 7828201 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5953. Min Range: -7.5953
Max Act: 6.8766. Min Act: -0.1700
Data Index: 7924585 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5953. Min Range: -7.5953
Max Act: 6.8766. Min Act: -0.1700
Data Index: 6243635 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5953. Min Range: -7.5953
Max Act: 6.8766. Min Act: -0.1700
Data Index: 7828208 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5953. Min Range: -7.5953
Max Act: 6.8766. Min Act: -0.1700
Data Index: 5007477 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19