Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3649 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.6388. Min Act: -0.1700
Data Index: 4747823 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.6075. Min Act: -0.1700
Data Index: 1069624 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.6388. Min Act: -0.1700
Data Index: 1612370 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.6388. Min Act: -0.1700
Data Index: 2356317 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.6388. Min Act: -0.1699
Data Index: 1573905 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.5762. Min Act: -0.1700
Data Index: 6497454 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.5449. Min Act: -0.1700
Data Index: 8253724 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4822. Min Act: -0.1700
Data Index: 3622969 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.5135. Min Act: -0.1700
Data Index: 6352500 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.5135. Min Act: -0.1700
Data Index: 1572915 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4822. Min Act: -0.1700
Data Index: 3882722 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4822. Min Act: -0.1700
Data Index: 3399685 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4822. Min Act: -0.1700
Data Index: 5555730 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4822. Min Act: -0.1700
Data Index: 184871 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4509. Min Act: -0.1700
Data Index: 1069621 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4509. Min Act: -0.1700
Data Index: 6497447 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4509. Min Act: -0.1700
Data Index: 6107925 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4509. Min Act: -0.1700
Data Index: 3666708 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4509. Min Act: -0.1700
Data Index: 6497445 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6388. Min Range: -3.6388
Max Act: 3.4509. Min Act: -0.1700
Data Index: 3622963 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19