Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.5423. Min Act: -0.1700
Data Index: 3048536 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.4173. Min Act: -0.1700
Data Index: 6954383 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.3236. Min Act: -0.1700
Data Index: 7134527 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.2923. Min Act: -0.1700
Data Index: 2045750 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.2923. Min Act: -0.1700
Data Index: 387271 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.3236. Min Act: -0.1700
Data Index: 866221 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.3236. Min Act: -0.1700
Data Index: 6062312 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.2923. Min Act: -0.1700
Data Index: 4084401 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.2611. Min Act: -0.1700
Data Index: 1378578 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.2923. Min Act: -0.1700
Data Index: 8346659 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.2611. Min Act: -0.1700
Data Index: 7680871 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.2298. Min Act: -0.1700
Data Index: 2569598 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.2298. Min Act: -0.1700
Data Index: 7303239 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.2298. Min Act: -0.1700
Data Index: 8484825 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.1986. Min Act: -0.1700
Data Index: 1182995 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.1986. Min Act: -0.1700
Data Index: 2830057 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.1986. Min Act: -0.1700
Data Index: 5502069 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.1361. Min Act: -0.1700
Data Index: 1206666 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.1673. Min Act: -0.1700
Data Index: 7334399 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5423. Min Range: -7.5423
Max Act: 7.1673. Min Act: -0.1700
Data Index: 5418583 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19