Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2841 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.5707. Min Act: -0.1700
Data Index: 1838014 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.4457. Min Act: -0.1700
Data Index: 7106377 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.4457. Min Act: -0.1700
Data Index: 1811493 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.3832. Min Act: -0.1700
Data Index: 4337876 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.2582. Min Act: -0.1700
Data Index: 6206883 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.1957. Min Act: -0.1700
Data Index: 7041261 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.2582. Min Act: -0.1700
Data Index: 3708212 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.2582. Min Act: -0.1700
Data Index: 8049678 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.1957. Min Act: -0.1700
Data Index: 573718 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.1957. Min Act: -0.1700
Data Index: 33881 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.1957. Min Act: -0.1700
Data Index: 3876157 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.1332. Min Act: -0.1700
Data Index: 632943 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.0707. Min Act: -0.1700
Data Index: 8283035 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.0707. Min Act: -0.1700
Data Index: 7918904 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.0082. Min Act: -0.1700
Data Index: 8212855 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.0707. Min Act: -0.1700
Data Index: 5622217 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.0082. Min Act: -0.1700
Data Index: 289832 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.0082. Min Act: -0.1700
Data Index: 4060571 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5707. Min Range: -8.5707
Max Act: 8.0082. Min Act: -0.1700
Data Index: 16346 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5707. Min Range: -8.5707
Max Act: 7.9770. Min Act: -0.1700
Data Index: 7574855 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19