Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 759 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.7874. Min Act: -0.1700
Data Index: 8620576 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.7249. Min Act: -0.1700
Data Index: 5880129 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.5999. Min Act: -0.1700
Data Index: 7471438 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.5686. Min Act: -0.1700
Data Index: 8609682 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.5374. Min Act: -0.1700
Data Index: 7793141 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.5374. Min Act: -0.1700
Data Index: 2928501 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.5686. Min Act: -0.1700
Data Index: 6278254 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.5374. Min Act: -0.1700
Data Index: 8503911 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.5374. Min Act: -0.1700
Data Index: 6491860 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.5374. Min Act: -0.1700
Data Index: 5773485 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.4749. Min Act: -0.1700
Data Index: 3007119 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.3811. Min Act: -0.1700
Data Index: 2265523 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.3811. Min Act: -0.1700
Data Index: 660728 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.3811. Min Act: -0.1700
Data Index: 1556642 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.3499. Min Act: -0.1700
Data Index: 8533791 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.3499. Min Act: -0.1700
Data Index: 4113408 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.3499. Min Act: -0.1700
Data Index: 6280986 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.2874. Min Act: -0.1700
Data Index: 1492078 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.2561. Min Act: -0.1700
Data Index: 8221364 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7874. Min Range: -6.7874
Max Act: 6.2561. Min Act: -0.1700
Data Index: 3473659 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19