Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.9934. Min Act: -0.1700
Data Index: 1090655 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.9309. Min Act: -0.1700
Data Index: 8045735 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.8371. Min Act: -0.1700
Data Index: 5619570 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.7746. Min Act: -0.1700
Data Index: 7085703 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.7434. Min Act: -0.1700
Data Index: 3606357 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.7121. Min Act: -0.1700
Data Index: 5152152 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.7121. Min Act: -0.1700
Data Index: 4956754 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.7121. Min Act: -0.1700
Data Index: 5824032 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.6809. Min Act: -0.1700
Data Index: 5534793 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.6809. Min Act: -0.1700
Data Index: 3841588 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.6809. Min Act: -0.1700
Data Index: 2580734 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.6496. Min Act: -0.1700
Data Index: 4369502 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.6496. Min Act: -0.1700
Data Index: 1229371 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.6184. Min Act: -0.1700
Data Index: 5928844 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.5871. Min Act: -0.1700
Data Index: 6771432 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.5871. Min Act: -0.1700
Data Index: 6803901 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.5559. Min Act: -0.1700
Data Index: 1072792 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.5559. Min Act: -0.1700
Data Index: 3028868 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.4934. Min Act: -0.1700
Data Index: 88401 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9934. Min Range: -6.9934
Max Act: 6.4621. Min Act: -0.1700
Data Index: 401175 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19