Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.5753. Min Act: -0.1700
Data Index: 7796688 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.5128. Min Act: -0.1700
Data Index: 8214711 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.4190. Min Act: -0.1700
Data Index: 5427320 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.4190. Min Act: -0.1700
Data Index: 1205026 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.4190. Min Act: -0.1700
Data Index: 6393504 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.3565. Min Act: -0.1700
Data Index: 6393503 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.3253. Min Act: -0.1700
Data Index: 2922238 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.3253. Min Act: -0.1700
Data Index: 6196506 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.2940. Min Act: -0.1700
Data Index: 3941571 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.2628. Min Act: -0.1700
Data Index: 3634173 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.2628. Min Act: -0.1700
Data Index: 5735315 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.1690. Min Act: -0.1700
Data Index: 7586670 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.2003. Min Act: -0.1700
Data Index: 3916669 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.2003. Min Act: -0.1700
Data Index: 378185 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.2003. Min Act: -0.1700
Data Index: 3994629 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.1378. Min Act: -0.1700
Data Index: 2654030 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.1690. Min Act: -0.1700
Data Index: 5075400 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.1378. Min Act: -0.1700
Data Index: 4115502 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.1690. Min Act: -0.1700
Data Index: 8171036 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5753. Min Range: -6.5753
Max Act: 6.1378. Min Act: -0.1700
Data Index: 5921692 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19