Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2941 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2827. Min Range: -7.2827
Max Act: 7.2827. Min Act: -0.1700
Data Index: 7565264 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.9390. Min Act: -0.1700
Data Index: 4773959 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.7827. Min Act: -0.1700
Data Index: 5776156 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.7202. Min Act: -0.1700
Data Index: 6216792 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.6577. Min Act: -0.1700
Data Index: 4290397 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.7202. Min Act: -0.1700
Data Index: 1153833 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.6890. Min Act: -0.1700
Data Index: 8475584 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.6577. Min Act: -0.1700
Data Index: 1534446 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.6265. Min Act: -0.1700
Data Index: 6860495 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.6890. Min Act: -0.1700
Data Index: 499696 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.6265. Min Act: -0.1700
Data Index: 53874 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.5952. Min Act: -0.1700
Data Index: 1658672 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.5952. Min Act: -0.1700
Data Index: 3814103 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.5640. Min Act: -0.1700
Data Index: 1534445 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.5327. Min Act: -0.1700
Data Index: 6314885 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.4390. Min Act: -0.1700
Data Index: 4173485 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.4077. Min Act: -0.1700
Data Index: 7639907 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.4077. Min Act: -0.1700
Data Index: 7565262 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.4077. Min Act: -0.1700
Data Index: 6348036 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2827. Min Range: -7.2827
Max Act: 6.3765. Min Act: -0.1700
Data Index: 4173487 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19