Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5781. Min Range: -5.5781
Max Act: 5.5781. Min Act: -0.1700
Data Index: 3954400 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5781. Min Range: -5.5781
Max Act: 5.5468. Min Act: -0.1700
Data Index: 6643851 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5781. Min Range: -5.5781
Max Act: 5.5781. Min Act: -0.1700
Data Index: 5544550 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5781. Min Range: -5.5781
Max Act: 5.3281. Min Act: -0.1700
Data Index: 6643848 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5781. Min Range: -5.5781
Max Act: 5.1718. Min Act: -0.1700
Data Index: 6980998 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5781. Min Range: -5.5781
Max Act: 5.0781. Min Act: -0.1700
Data Index: 5414056 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.9218. Min Act: -0.1700
Data Index: 5756247 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.8593. Min Act: -0.1700
Data Index: 5197083 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.8593. Min Act: -0.1700
Data Index: 7016684 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.8281. Min Act: -0.1700
Data Index: 3026481 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.8281. Min Act: -0.1700
Data Index: 3211520 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.7656. Min Act: -0.1700
Data Index: 1180129 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.7968. Min Act: -0.1700
Data Index: 3997728 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.6718. Min Act: -0.1700
Data Index: 992548 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.7031. Min Act: -0.1700
Data Index: 894748 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.7031. Min Act: -0.1700
Data Index: 1924239 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.7031. Min Act: -0.1700
Data Index: 4680842 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.6718. Min Act: -0.1700
Data Index: 4114792 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.6718. Min Act: -0.1700
Data Index: 8359445 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5781. Min Range: -5.5781
Max Act: 4.6406. Min Act: -0.1700
Data Index: 1670405 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19