Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5435 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3706. Min Range: -7.3706
Max Act: 7.3706. Min Act: -0.1700
Data Index: 7620630 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3706. Min Range: -7.3706
Max Act: 7.1518. Min Act: -0.1700
Data Index: 6616514 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3706. Min Range: -7.3706
Max Act: 7.0581. Min Act: -0.1700
Data Index: 1621145 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3706. Min Range: -7.3706
Max Act: 7.0268. Min Act: -0.1700
Data Index: 6968727 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3706. Min Range: -7.3706
Max Act: 7.0268. Min Act: -0.1700
Data Index: 1723894 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3706. Min Range: -7.3706
Max Act: 7.0268. Min Act: -0.1700
Data Index: 5027131 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.9956. Min Act: -0.1700
Data Index: 85118 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.9331. Min Act: -0.1700
Data Index: 4306668 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.8706. Min Act: -0.1700
Data Index: 2911792 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.8706. Min Act: -0.1700
Data Index: 5303306 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.8393. Min Act: -0.1700
Data Index: 4327930 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.7768. Min Act: -0.1700
Data Index: 486601 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.7456. Min Act: -0.1700
Data Index: 4927809 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.7768. Min Act: -0.1700
Data Index: 1603935 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.7768. Min Act: -0.1700
Data Index: 2307431 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.7768. Min Act: -0.1700
Data Index: 7645430 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.7456. Min Act: -0.1700
Data Index: 7800496 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.7143. Min Act: -0.1700
Data Index: 6217693 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.6831. Min Act: -0.1700
Data Index: 8717586 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3706. Min Range: -7.3706
Max Act: 6.6831. Min Act: -0.1700
Data Index: 3192750 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19