Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1296 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3308. Min Range: -5.3308
Max Act: 5.3308. Min Act: -0.1700
Data Index: 6492100 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3308. Min Range: -5.3308
Max Act: 5.2371. Min Act: -0.1700
Data Index: 1155645 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3308. Min Range: -5.3308
Max Act: 5.1746. Min Act: -0.1700
Data Index: 1424932 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3308. Min Range: -5.3308
Max Act: 5.1746. Min Act: -0.1700
Data Index: 5772129 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3308. Min Range: -5.3308
Max Act: 5.1433. Min Act: -0.1700
Data Index: 3058580 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3308. Min Range: -5.3308
Max Act: 5.0496. Min Act: -0.1700
Data Index: 4389256 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3308. Min Range: -5.3308
Max Act: 5.0496. Min Act: -0.1700
Data Index: 413576 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3308. Min Range: -5.3308
Max Act: 5.0496. Min Act: -0.1700
Data Index: 1580439 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3308. Min Range: -5.3308
Max Act: 5.0183. Min Act: -0.1700
Data Index: 8238356 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3308. Min Range: -5.3308
Max Act: 5.0183. Min Act: -0.1700
Data Index: 5807414 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3308. Min Range: -5.3308
Max Act: 4.9871. Min Act: -0.1700
Data Index: 6546126 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3308. Min Range: -5.3308
Max Act: 4.9246. Min Act: -0.1700
Data Index: 4911662 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3308. Min Range: -5.3308
Max Act: 4.9246. Min Act: -0.1700
Data Index: 6253814 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3308. Min Range: -5.3308
Max Act: 4.8933. Min Act: -0.1700
Data Index: 810924 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3308. Min Range: -5.3308
Max Act: 4.8933. Min Act: -0.1700
Data Index: 3481832 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3308. Min Range: -5.3308
Max Act: 4.8933. Min Act: -0.1700
Data Index: 4592999 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3308. Min Range: -5.3308
Max Act: 4.8933. Min Act: -0.1700
Data Index: 967687 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3308. Min Range: -5.3308
Max Act: 4.8933. Min Act: -0.1700
Data Index: 4453405 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3308. Min Range: -5.3308
Max Act: 4.8621. Min Act: -0.1700
Data Index: 7808837 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3308. Min Range: -5.3308
Max Act: 4.8621. Min Act: -0.1700
Data Index: 2952810 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19