Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3855 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2638. Min Range: -5.2638
Max Act: 5.2638. Min Act: -0.1700
Data Index: 4402522 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2638. Min Range: -5.2638
Max Act: 5.1388. Min Act: -0.1700
Data Index: 1899095 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2638. Min Range: -5.2638
Max Act: 5.0450. Min Act: -0.1700
Data Index: 6025014 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2638. Min Range: -5.2638
Max Act: 5.0450. Min Act: -0.1700
Data Index: 6025015 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2638. Min Range: -5.2638
Max Act: 5.0763. Min Act: -0.1700
Data Index: 3036835 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2638. Min Range: -5.2638
Max Act: 5.0138. Min Act: -0.1700
Data Index: 6025013 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2638. Min Range: -5.2638
Max Act: 5.0138. Min Act: -0.1700
Data Index: 1899087 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.9513. Min Act: -0.1700
Data Index: 6659675 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.9513. Min Act: -0.1700
Data Index: 8658843 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.9513. Min Act: -0.1700
Data Index: 5271366 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.9200. Min Act: -0.1700
Data Index: 2407037 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.9200. Min Act: -0.1700
Data Index: 8507986 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.9200. Min Act: -0.1700
Data Index: 3530717 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.9200. Min Act: -0.1700
Data Index: 1548087 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.9513. Min Act: -0.1700
Data Index: 8476433 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.8888. Min Act: -0.1700
Data Index: 2178606 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.8888. Min Act: -0.1700
Data Index: 4415427 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.8888. Min Act: -0.1700
Data Index: 346355 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.8888. Min Act: -0.1700
Data Index: 8507984 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2638. Min Range: -5.2638
Max Act: 4.8888. Min Act: -0.1700
Data Index: 2843960 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19