Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0874. Min Range: -11.0874
Max Act: 11.0874. Min Act: -0.1700
Data Index: 1954967 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0874. Min Range: -11.0874
Max Act: 10.4624. Min Act: -0.1700
Data Index: 2109987 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0874. Min Range: -11.0874
Max Act: 9.9624. Min Act: -0.1700
Data Index: 2529989 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0874. Min Range: -11.0874
Max Act: 9.5874. Min Act: -0.1700
Data Index: 1924457 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0874. Min Range: -11.0874
Max Act: 9.5249. Min Act: -0.1700
Data Index: 6017089 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0874. Min Range: -11.0874
Max Act: 9.3374. Min Act: -0.1700
Data Index: 21191 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0874. Min Range: -11.0874
Max Act: 9.0874. Min Act: -0.1700
Data Index: 2329261 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.9624. Min Act: -0.1700
Data Index: 5337722 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.9624. Min Act: -0.1700
Data Index: 3816871 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.8999. Min Act: -0.1700
Data Index: 6227708 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.8374. Min Act: -0.1700
Data Index: 6952440 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.8374. Min Act: -0.1700
Data Index: 4312572 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.8374. Min Act: -0.1700
Data Index: 2142959 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.6499. Min Act: -0.1700
Data Index: 3052462 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.6499. Min Act: -0.1700
Data Index: 7474840 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.6499. Min Act: -0.1700
Data Index: 7716748 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.6499. Min Act: -0.1700
Data Index: 1314015 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.6499. Min Act: -0.1700
Data Index: 3800878 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.5874. Min Act: -0.1700
Data Index: 3457967 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0874. Min Range: -11.0874
Max Act: 8.5874. Min Act: -0.1700
Data Index: 7130523 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19