Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.5110. Min Act: -0.1700
Data Index: 6490933 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.2610. Min Act: -0.1700
Data Index: 3950931 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.2298. Min Act: -0.1700
Data Index: 5055671 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.1360. Min Act: -0.1700
Data Index: 7205598 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.1360. Min Act: -0.1700
Data Index: 2433142 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.1360. Min Act: -0.1700
Data Index: 1513315 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.0735. Min Act: -0.1700
Data Index: 5622558 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.0735. Min Act: -0.1700
Data Index: 3689268 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.0110. Min Act: -0.1700
Data Index: 3689269 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.0423. Min Act: -0.1700
Data Index: 4090168 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5110. Min Range: -6.5110
Max Act: 6.0110. Min Act: -0.1700
Data Index: 8564957 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5110. Min Range: -6.5110
Max Act: 5.9798. Min Act: -0.1700
Data Index: 5947197 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5110. Min Range: -6.5110
Max Act: 5.9798. Min Act: -0.1700
Data Index: 4520367 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5110. Min Range: -6.5110
Max Act: 5.9798. Min Act: -0.1700
Data Index: 5149504 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5110. Min Range: -6.5110
Max Act: 5.9485. Min Act: -0.1700
Data Index: 4274843 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5110. Min Range: -6.5110
Max Act: 5.9173. Min Act: -0.1698
Data Index: 5585231 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5110. Min Range: -6.5110
Max Act: 5.8548. Min Act: -0.1700
Data Index: 2660704 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5110. Min Range: -6.5110
Max Act: 5.8548. Min Act: -0.1700
Data Index: 4145721 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5110. Min Range: -6.5110
Max Act: 5.8548. Min Act: -0.1700
Data Index: 8403318 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5110. Min Range: -6.5110
Max Act: 5.8235. Min Act: -0.1700
Data Index: 6861060 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19