Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3758 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.2463. Min Act: -0.1700
Data Index: 2067203 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.1213. Min Act: -0.1700
Data Index: 2256836 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.1838. Min Act: -0.1700
Data Index: 6443081 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.1838. Min Act: -0.1700
Data Index: 3366561 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.1213. Min Act: -0.1700
Data Index: 5546797 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.1213. Min Act: -0.1700
Data Index: 1113749 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.1213. Min Act: -0.1700
Data Index: 112255 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2463. Min Range: -8.2463
Max Act: 7.9963. Min Act: -0.1700
Data Index: 8627021 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.0588. Min Act: -0.1700
Data Index: 8809718 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.0588. Min Act: -0.1700
Data Index: 8765850 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.0588. Min Act: -0.1700
Data Index: 1862129 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2463. Min Range: -8.2463
Max Act: 8.0588. Min Act: -0.1700
Data Index: 4460602 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2463. Min Range: -8.2463
Max Act: 7.9963. Min Act: -0.1700
Data Index: 8345708 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2463. Min Range: -8.2463
Max Act: 7.9963. Min Act: -0.1700
Data Index: 5500606 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2463. Min Range: -8.2463
Max Act: 7.9963. Min Act: -0.1700
Data Index: 4518123 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2463. Min Range: -8.2463
Max Act: 7.9963. Min Act: -0.1700
Data Index: 3783298 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2463. Min Range: -8.2463
Max Act: 7.9963. Min Act: -0.1700
Data Index: 3330174 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2463. Min Range: -8.2463
Max Act: 7.9963. Min Act: -0.1700
Data Index: 3741185 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2463. Min Range: -8.2463
Max Act: 7.9963. Min Act: -0.1700
Data Index: 685161 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2463. Min Range: -8.2463
Max Act: 7.9963. Min Act: -0.1700
Data Index: 3727362 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19