Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3758 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.9892. Min Act: -0.1700
Data Index: 3608907 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.9267. Min Act: -0.1700
Data Index: 4259374 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.9580. Min Act: -0.1700
Data Index: 5872229 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.8955. Min Act: -0.1700
Data Index: 3159436 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.8955. Min Act: -0.1700
Data Index: 8024783 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.8642. Min Act: -0.1700
Data Index: 6072099 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.8017. Min Act: -0.1700
Data Index: 138071 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.8017. Min Act: -0.1700
Data Index: 4937729 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.7080. Min Act: -0.1700
Data Index: 8574 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.7392. Min Act: -0.1700
Data Index: 4394158 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.7080. Min Act: -0.1700
Data Index: 8633827 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6767. Min Act: -0.1700
Data Index: 7523811 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6455. Min Act: -0.1700
Data Index: 2593814 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6142. Min Act: -0.1700
Data Index: 2812848 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.5830. Min Act: -0.1700
Data Index: 8625377 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6142. Min Act: -0.1700
Data Index: 8028767 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.5517. Min Act: -0.1700
Data Index: 638492 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.5205. Min Act: -0.1700
Data Index: 4923541 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.5205. Min Act: -0.1700
Data Index: 2710829 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.5517. Min Act: -0.1700
Data Index: 6501550 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19