Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2007 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.9369. Min Act: -0.1700
Data Index: 7634789 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.9369. Min Act: -0.1700
Data Index: 3745843 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.7494. Min Act: -0.1700
Data Index: 1524544 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.6869. Min Act: -0.1700
Data Index: 2775383 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.7494. Min Act: -0.1700
Data Index: 4833514 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.6869. Min Act: -0.1700
Data Index: 3177938 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.6869. Min Act: -0.1700
Data Index: 493001 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.6244. Min Act: -0.1700
Data Index: 4842413 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.6244. Min Act: -0.1700
Data Index: 1556936 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.6244. Min Act: -0.1700
Data Index: 7659926 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.6244. Min Act: -0.1700
Data Index: 7196018 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.6244. Min Act: -0.1700
Data Index: 6560334 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.5619. Min Act: -0.1700
Data Index: 1561555 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.5619. Min Act: -0.1700
Data Index: 5582323 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.6244. Min Act: -0.1700
Data Index: 7009045 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.5619. Min Act: -0.1700
Data Index: 3610664 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.5619. Min Act: -0.1700
Data Index: 2277345 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.5619. Min Act: -0.1700
Data Index: 2565930 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.5619. Min Act: -0.1700
Data Index: 41285 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9369. Min Range: -8.9369
Max Act: 8.4994. Min Act: -0.1700
Data Index: 2108426 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19