Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3908 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.8583. Min Act: -0.1700
Data Index: 479607 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.7958. Min Act: -0.1700
Data Index: 4336164 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.7958. Min Act: -0.1700
Data Index: 5297855 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.7646. Min Act: -0.1700
Data Index: 7680659 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.7333. Min Act: -0.1700
Data Index: 6334939 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.7021. Min Act: -0.1700
Data Index: 3895631 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6708. Min Act: -0.1700
Data Index: 4221997 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.7021. Min Act: -0.1700
Data Index: 1355828 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.7021. Min Act: -0.1700
Data Index: 5754698 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.7021. Min Act: -0.1700
Data Index: 6029038 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6396. Min Act: -0.1700
Data Index: 8552498 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6708. Min Act: -0.1700
Data Index: 197265 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6708. Min Act: -0.1700
Data Index: 1164609 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6708. Min Act: -0.1700
Data Index: 7828057 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6708. Min Act: -0.1700
Data Index: 3274897 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6396. Min Act: -0.1700
Data Index: 3518605 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6083. Min Act: -0.1700
Data Index: 6028788 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6396. Min Act: -0.1700
Data Index: 5712730 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6396. Min Act: -0.1700
Data Index: 5405429 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8583. Min Range: -5.8583
Max Act: 5.6396. Min Act: -0.1700
Data Index: 4250003 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19