Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.8339. Min Act: -0.1700
Data Index: 6909645 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.6777. Min Act: -0.1700
Data Index: 4135248 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.6777. Min Act: -0.1700
Data Index: 495203 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.5839. Min Act: -0.1700
Data Index: 6932810 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.5527. Min Act: -0.1700
Data Index: 3087237 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.5527. Min Act: -0.1700
Data Index: 4670998 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.5839. Min Act: -0.1700
Data Index: 7921549 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.5527. Min Act: -0.1700
Data Index: 2352830 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.5214. Min Act: -0.1700
Data Index: 5258114 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.5214. Min Act: -0.1700
Data Index: 6715305 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.5214. Min Act: -0.1700
Data Index: 7229302 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.4589. Min Act: -0.1700
Data Index: 210431 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.4589. Min Act: -0.1700
Data Index: 4582061 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.4589. Min Act: -0.1700
Data Index: 5289510 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.4589. Min Act: -0.1700
Data Index: 1160620 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.4589. Min Act: -0.1700
Data Index: 3820525 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.4589. Min Act: -0.1700
Data Index: 98413 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.3964. Min Act: -0.1700
Data Index: 1093716 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.4277. Min Act: -0.1700
Data Index: 3706905 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8339. Min Range: -6.8339
Max Act: 6.4277. Min Act: -0.1700
Data Index: 1901903 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19