Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5095 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4540. Min Range: -9.4540
Max Act: 9.4540. Min Act: -0.1700
Data Index: 5648178 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4540. Min Range: -9.4540
Max Act: 9.0790. Min Act: -0.1700
Data Index: 7757433 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.9540. Min Act: -0.1700
Data Index: 4840138 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.9540. Min Act: -0.1700
Data Index: 3082311 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.9540. Min Act: -0.1700
Data Index: 7187544 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.8915. Min Act: -0.1700
Data Index: 3451966 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.8290. Min Act: -0.1700
Data Index: 4411763 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.7665. Min Act: -0.1700
Data Index: 3082305 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.7665. Min Act: -0.1700
Data Index: 8688107 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.6415. Min Act: -0.1700
Data Index: 1571011 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.7040. Min Act: -0.1700
Data Index: 4557893 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.6415. Min Act: -0.1700
Data Index: 2681672 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.6415. Min Act: -0.1700
Data Index: 936849 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.5790. Min Act: -0.1700
Data Index: 1813500 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.5790. Min Act: -0.1700
Data Index: 2012188 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.5790. Min Act: -0.1700
Data Index: 6161643 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.5790. Min Act: -0.1700
Data Index: 804961 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.4540. Min Act: -0.1700
Data Index: 3973103 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.4540. Min Act: -0.1700
Data Index: 8465883 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4540. Min Range: -9.4540
Max Act: 8.4540. Min Act: -0.1700
Data Index: 3451968 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19