Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2002 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2710. Min Range: -8.2710
Max Act: 8.2710. Min Act: -0.1700
Data Index: 8403178 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2710. Min Range: -8.2710
Max Act: 8.0210. Min Act: -0.1700
Data Index: 625746 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2710. Min Range: -8.2710
Max Act: 8.0210. Min Act: -0.1700
Data Index: 7184693 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.9585. Min Act: -0.1700
Data Index: 3243055 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.9585. Min Act: -0.1700
Data Index: 30507 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.8335. Min Act: -0.1700
Data Index: 3744684 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.8335. Min Act: -0.1700
Data Index: 645484 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.8960. Min Act: -0.1700
Data Index: 2048709 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.8335. Min Act: -0.1700
Data Index: 215891 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.8335. Min Act: -0.1700
Data Index: 4542366 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.7085. Min Act: -0.1700
Data Index: 2643104 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.7710. Min Act: -0.1700
Data Index: 6154909 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.7710. Min Act: -0.1700
Data Index: 6116914 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.7710. Min Act: -0.1700
Data Index: 4196239 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.7710. Min Act: -0.1700
Data Index: 4728091 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.7710. Min Act: -0.1700
Data Index: 1834586 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.7085. Min Act: -0.1700
Data Index: 295270 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.7085. Min Act: -0.1700
Data Index: 1801158 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.6460. Min Act: -0.1700
Data Index: 5136659 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2710. Min Range: -8.2710
Max Act: 7.7085. Min Act: -0.1700
Data Index: 2206709 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19