Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.5026. Min Act: -0.1700
Data Index: 2779791 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.4089. Min Act: -0.1700
Data Index: 7385955 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.3776. Min Act: -0.1700
Data Index: 1947355 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.4089. Min Act: -0.1700
Data Index: 1820378 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.3776. Min Act: -0.1700
Data Index: 1405088 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.3776. Min Act: -0.1700
Data Index: 2398631 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.3776. Min Act: -0.1700
Data Index: 8552065 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.3464. Min Act: -0.1700
Data Index: 6457545 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.2839. Min Act: -0.1700
Data Index: 966410 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.2526. Min Act: -0.1700
Data Index: 5690364 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.2214. Min Act: -0.1700
Data Index: 7406418 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.2214. Min Act: -0.1700
Data Index: 7125938 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.1901. Min Act: -0.1700
Data Index: 2804849 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.1589. Min Act: -0.1700
Data Index: 3060465 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.1901. Min Act: -0.1700
Data Index: 3321533 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.1589. Min Act: -0.1700
Data Index: 3303526 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.1901. Min Act: -0.1700
Data Index: 2247958 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.1589. Min Act: -0.1700
Data Index: 3005384 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.1589. Min Act: -0.1700
Data Index: 669498 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5026. Min Range: -4.5026
Max Act: 4.1589. Min Act: -0.1700
Data Index: 1414585 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19