Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3259 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.5758. Min Act: -0.1700
Data Index: 6686292 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.5446. Min Act: -0.1700
Data Index: 6815495 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.5446. Min Act: -0.1700
Data Index: 2382986 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.5133. Min Act: -0.1700
Data Index: 4353603 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.4821. Min Act: -0.1700
Data Index: 4889770 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.4196. Min Act: -0.1700
Data Index: 1221065 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.4508. Min Act: -0.1700
Data Index: 5940995 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.4196. Min Act: -0.1700
Data Index: 2137603 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.3883. Min Act: -0.1700
Data Index: 2825651 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.3258. Min Act: -0.1700
Data Index: 860199 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.3258. Min Act: -0.1700
Data Index: 6245277 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.2946. Min Act: -0.1700
Data Index: 4893672 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.2946. Min Act: -0.1700
Data Index: 2061141 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.2633. Min Act: -0.1700
Data Index: 4138486 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.2321. Min Act: -0.1700
Data Index: 6046136 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.2321. Min Act: -0.1700
Data Index: 3761006 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.2321. Min Act: -0.1700
Data Index: 6911171 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.2008. Min Act: -0.1700
Data Index: 3404619 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.2008. Min Act: -0.1700
Data Index: 2910558 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5758. Min Range: -5.5758
Max Act: 5.1696. Min Act: -0.1700
Data Index: 7204462 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19