Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 775 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.3477. Min Act: -0.1700
Data Index: 155589 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.3165. Min Act: -0.1700
Data Index: 342138 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.2852. Min Act: -0.1699
Data Index: 1575536 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.2540. Min Act: -0.1700
Data Index: 2158354 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.2540. Min Act: -0.1690
Data Index: 8476912 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.2227. Min Act: -0.1700
Data Index: 5733396 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.1915. Min Act: -0.1700
Data Index: 2301069 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.1915. Min Act: -0.1700
Data Index: 6405013 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.1602. Min Act: -0.1700
Data Index: 5521243 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.1602. Min Act: -0.1700
Data Index: 1068106 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.1290. Min Act: -0.1695
Data Index: 4244591 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.1290. Min Act: -0.1700
Data Index: 4699333 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.0977. Min Act: -0.1700
Data Index: 2742029 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.0977. Min Act: -0.1699
Data Index: 7517975 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.0977. Min Act: -0.1700
Data Index: 8462254 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.0977. Min Act: -0.1700
Data Index: 3688508 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3477. Min Range: -5.3477
Max Act: 5.0040. Min Act: -0.1700
Data Index: 6549538 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3477. Min Range: -5.3477
Max Act: 4.9727. Min Act: -0.1700
Data Index: 1455634 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3477. Min Range: -5.3477
Max Act: 4.9102. Min Act: -0.1700
Data Index: 7683917 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3477. Min Range: -5.3477
Max Act: 4.8790. Min Act: -0.1700
Data Index: 316600 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19