Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.8783. Min Act: -0.1700
Data Index: 4976519 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.8471. Min Act: -0.1700
Data Index: 7078141 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7846. Min Act: -0.1700
Data Index: 6540888 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7846. Min Act: -0.1700
Data Index: 3731983 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7846. Min Act: -0.1700
Data Index: 7337031 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7533. Min Act: -0.1700
Data Index: 2991904 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7221. Min Act: -0.1700
Data Index: 2521204 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7533. Min Act: -0.1700
Data Index: 7593596 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7221. Min Act: -0.1700
Data Index: 8758519 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7221. Min Act: -0.1700
Data Index: 8054151 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7221. Min Act: -0.1700
Data Index: 1240527 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7221. Min Act: -0.1700
Data Index: 7803169 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.6908. Min Act: -0.1700
Data Index: 1473909 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.6908. Min Act: -0.1700
Data Index: 6299046 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.6908. Min Act: -0.1700
Data Index: 3731969 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.7221. Min Act: -0.1700
Data Index: 6585126 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.6908. Min Act: -0.1700
Data Index: 1459392 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.6596. Min Act: -0.1700
Data Index: 3027059 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.6596. Min Act: -0.1700
Data Index: 407144 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8783. Min Range: -4.8783
Max Act: 4.6283. Min Act: -0.1700
Data Index: 5175948 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19