Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5193 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.8590. Min Act: -0.1700
Data Index: 6765381 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.8277. Min Act: -0.1700
Data Index: 4196785 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.6715. Min Act: -0.1700
Data Index: 6582616 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.6090. Min Act: -0.1700
Data Index: 5418600 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.6090. Min Act: -0.1700
Data Index: 8325352 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.6090. Min Act: -0.1700
Data Index: 5942642 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.6090. Min Act: -0.1700
Data Index: 165551 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.5777. Min Act: -0.1700
Data Index: 734109 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.5777. Min Act: -0.1700
Data Index: 1539578 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.5465. Min Act: -0.1700
Data Index: 2611926 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.5152. Min Act: -0.1700
Data Index: 8707844 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.5152. Min Act: -0.1700
Data Index: 498240 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.4840. Min Act: -0.1700
Data Index: 5887389 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.4840. Min Act: -0.1700
Data Index: 1944417 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.5152. Min Act: -0.1700
Data Index: 340900 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.4840. Min Act: -0.1700
Data Index: 813763 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.4840. Min Act: -0.1700
Data Index: 5370892 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.4840. Min Act: -0.1700
Data Index: 3531584 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.4215. Min Act: -0.1700
Data Index: 6382028 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8590. Min Range: -5.8590
Max Act: 5.4215. Min Act: -0.1700
Data Index: 7316485 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19