Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3893 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2892. Min Range: -6.2892
Max Act: 6.2892. Min Act: -0.1700
Data Index: 8127491 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2892. Min Range: -6.2892
Max Act: 6.2579. Min Act: -0.1700
Data Index: 6051859 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2892. Min Range: -6.2892
Max Act: 6.0704. Min Act: -0.1700
Data Index: 1382081 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2892. Min Range: -6.2892
Max Act: 6.0392. Min Act: -0.1700
Data Index: 193938 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.9142. Min Act: -0.1700
Data Index: 4791441 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.9142. Min Act: -0.1700
Data Index: 7533974 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8829. Min Act: -0.1700
Data Index: 5555454 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8829. Min Act: -0.1700
Data Index: 1918442 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8829. Min Act: -0.1700
Data Index: 3455357 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8517. Min Act: -0.1700
Data Index: 4524282 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8517. Min Act: -0.1700
Data Index: 4037546 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8517. Min Act: -0.1700
Data Index: 1493428 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8517. Min Act: -0.1700
Data Index: 6625388 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8204. Min Act: -0.1700
Data Index: 277664 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8204. Min Act: -0.1700
Data Index: 8392885 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8204. Min Act: -0.1700
Data Index: 6483097 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.8204. Min Act: -0.1700
Data Index: 5900072 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.7892. Min Act: -0.1700
Data Index: 1375459 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.7892. Min Act: -0.1700
Data Index: 4905825 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2892. Min Range: -6.2892
Max Act: 5.7892. Min Act: -0.1700
Data Index: 1733869 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19