Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.9184. Min Act: -0.1700
Data Index: 8696493 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.3559. Min Act: -0.1700
Data Index: 5583836 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.2934. Min Act: -0.1700
Data Index: 1485410 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.2309. Min Act: -0.1700
Data Index: 6016862 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.2622. Min Act: -0.1700
Data Index: 8731464 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.1997. Min Act: -0.1700
Data Index: 2613370 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.1997. Min Act: -0.1700
Data Index: 4853178 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.1372. Min Act: -0.1700
Data Index: 2272868 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.0434. Min Act: -0.1700
Data Index: 4502745 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.0747. Min Act: -0.1700
Data Index: 3294954 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.0747. Min Act: -0.1700
Data Index: 6347732 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.0434. Min Act: -0.1700
Data Index: 3420465 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.0122. Min Act: -0.1700
Data Index: 1817794 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.0122. Min Act: -0.1700
Data Index: 8691797 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9184. Min Range: -5.9184
Max Act: 5.0122. Min Act: -0.1700
Data Index: 7089326 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9184. Min Range: -5.9184
Max Act: 4.9809. Min Act: -0.1700
Data Index: 7025594 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9184. Min Range: -5.9184
Max Act: 4.9809. Min Act: -0.1700
Data Index: 7239473 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9184. Min Range: -5.9184
Max Act: 4.9809. Min Act: -0.1700
Data Index: 117 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9184. Min Range: -5.9184
Max Act: 4.9497. Min Act: -0.1700
Data Index: 3320447 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9184. Min Range: -5.9184
Max Act: 4.9497. Min Act: -0.1700
Data Index: 2789649 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19