Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1551 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5934. Min Range: -7.5934
Max Act: 7.5934. Min Act: -0.1699
Data Index: 1600070 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5934. Min Range: -7.5934
Max Act: 7.2496. Min Act: -0.1700
Data Index: 4393507 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5934. Min Range: -7.5934
Max Act: 7.1559. Min Act: -0.1700
Data Index: 8405771 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5934. Min Range: -7.5934
Max Act: 7.1246. Min Act: -0.1700
Data Index: 8382158 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5934. Min Range: -7.5934
Max Act: 7.0621. Min Act: -0.1700
Data Index: 6297982 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5934. Min Range: -7.5934
Max Act: 7.0621. Min Act: -0.1700
Data Index: 858028 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5934. Min Range: -7.5934
Max Act: 7.0309. Min Act: -0.1700
Data Index: 2676402 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5934. Min Range: -7.5934
Max Act: 7.0309. Min Act: -0.1700
Data Index: 7136928 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.9996. Min Act: -0.1700
Data Index: 8219087 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.9684. Min Act: -0.1700
Data Index: 635514 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.9684. Min Act: -0.1700
Data Index: 6521555 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.9371. Min Act: -0.1700
Data Index: 8405778 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.9684. Min Act: -0.1700
Data Index: 2703421 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.9371. Min Act: -0.1700
Data Index: 1231684 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.9371. Min Act: -0.1700
Data Index: 8416894 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.9059. Min Act: -0.1700
Data Index: 4718154 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.8746. Min Act: -0.1700
Data Index: 234827 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.8746. Min Act: -0.1700
Data Index: 8382157 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.8746. Min Act: -0.1700
Data Index: 18713 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5934. Min Range: -7.5934
Max Act: 6.8746. Min Act: -0.1700
Data Index: 5207528 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19