Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5895 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2031. Min Range: -5.2031
Max Act: 5.2031. Min Act: -0.1700
Data Index: 8470353 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2031. Min Range: -5.2031
Max Act: 5.2031. Min Act: -0.1700
Data Index: 4028268 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2031. Min Range: -5.2031
Max Act: 5.1718. Min Act: -0.1700
Data Index: 2516261 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2031. Min Range: -5.2031
Max Act: 5.0468. Min Act: -0.1700
Data Index: 2471044 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2031. Min Range: -5.2031
Max Act: 5.0156. Min Act: -0.1700
Data Index: 51962 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.9843. Min Act: -0.1700
Data Index: 975639 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.9218. Min Act: -0.1700
Data Index: 51967 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.8906. Min Act: -0.1700
Data Index: 7205708 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.8281. Min Act: -0.1700
Data Index: 2689385 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.8593. Min Act: -0.1700
Data Index: 6416920 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.8281. Min Act: -0.1700
Data Index: 8317408 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.7968. Min Act: -0.1700
Data Index: 975741 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.8281. Min Act: -0.1700
Data Index: 7571135 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.8281. Min Act: -0.1700
Data Index: 3894152 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.8281. Min Act: -0.1700
Data Index: 2207952 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.7968. Min Act: -0.1700
Data Index: 2898260 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.7656. Min Act: -0.1700
Data Index: 3801914 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.7656. Min Act: -0.1700
Data Index: 3644058 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.7656. Min Act: -0.1700
Data Index: 2310835 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2031. Min Range: -5.2031
Max Act: 4.7656. Min Act: -0.1700
Data Index: 2256760 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19