Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3527 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.9569. Min Act: -0.1700
Data Index: 1690732 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.9256. Min Act: -0.1700
Data Index: 5350327 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.7069. Min Act: -0.1700
Data Index: 7262866 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.7069. Min Act: -0.1700
Data Index: 8529962 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.6444. Min Act: -0.1700
Data Index: 6513942 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.6444. Min Act: -0.1700
Data Index: 8733851 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.6131. Min Act: -0.1700
Data Index: 4046647 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.6131. Min Act: -0.1700
Data Index: 251613 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.5819. Min Act: -0.1700
Data Index: 7928765 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.5506. Min Act: -0.1700
Data Index: 5072443 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.5194. Min Act: -0.1700
Data Index: 4104678 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.4881. Min Act: -0.1700
Data Index: 1089287 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.4881. Min Act: -0.1700
Data Index: 4723825 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.4881. Min Act: -0.1700
Data Index: 7887454 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.4881. Min Act: -0.1700
Data Index: 1504820 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.4256. Min Act: -0.1700
Data Index: 7663907 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.4881. Min Act: -0.1700
Data Index: 3355571 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.3944. Min Act: -0.1700
Data Index: 5410525 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.3944. Min Act: -0.1700
Data Index: 5201354 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9569. Min Range: -5.9569
Max Act: 5.4256. Min Act: -0.1700
Data Index: 6776741 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19