Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2158. Min Range: -8.2158
Max Act: 8.2158. Min Act: -0.1700
Data Index: 7918412 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.9658. Min Act: -0.1700
Data Index: 2617517 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.7783. Min Act: -0.1700
Data Index: 8065404 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.7158. Min Act: -0.1700
Data Index: 6959340 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.6533. Min Act: -0.1700
Data Index: 6957404 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.5908. Min Act: -0.1700
Data Index: 3447616 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.6533. Min Act: -0.1700
Data Index: 1095120 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.5908. Min Act: -0.1700
Data Index: 3642038 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.5908. Min Act: -0.1700
Data Index: 4635842 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.5595. Min Act: -0.1700
Data Index: 7323509 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.5595. Min Act: -0.1700
Data Index: 3504399 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.5595. Min Act: -0.1700
Data Index: 4027360 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.5595. Min Act: -0.1700
Data Index: 5253318 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.5908. Min Act: -0.1700
Data Index: 8513927 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.5283. Min Act: -0.1700
Data Index: 124256 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.4970. Min Act: -0.1700
Data Index: 3261543 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.4970. Min Act: -0.1700
Data Index: 7299953 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.4970. Min Act: -0.1700
Data Index: 8430982 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.4658. Min Act: -0.1700
Data Index: 4573995 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2158. Min Range: -8.2158
Max Act: 7.4658. Min Act: -0.1700
Data Index: 5940567 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19