Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.9599. Min Act: -0.1700
Data Index: 4387300 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.8349. Min Act: -0.1700
Data Index: 7190699 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.7724. Min Act: -0.1700
Data Index: 3540161 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.5849. Min Act: -0.1700
Data Index: 6744235 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.5849. Min Act: -0.1700
Data Index: 7295543 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.5224. Min Act: -0.1700
Data Index: 3535460 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.5224. Min Act: -0.1700
Data Index: 2612865 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.4599. Min Act: -0.1700
Data Index: 2336294 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.3974. Min Act: -0.1700
Data Index: 1784374 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.3974. Min Act: -0.1700
Data Index: 4955340 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.3661. Min Act: -0.1700
Data Index: 5569060 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.3661. Min Act: -0.1700
Data Index: 1278529 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.3349. Min Act: -0.1700
Data Index: 7660372 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.3349. Min Act: -0.1700
Data Index: 8535466 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.3349. Min Act: -0.1700
Data Index: 4703336 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.3036. Min Act: -0.1700
Data Index: 3551129 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.2724. Min Act: -0.1700
Data Index: 5475706 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.2724. Min Act: -0.1700
Data Index: 5887447 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.2724. Min Act: -0.1700
Data Index: 540790 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9599. Min Range: -7.9599
Max Act: 7.2411. Min Act: -0.1700
Data Index: 6920964 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19