Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5549 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3895. Min Range: -9.3895
Max Act: 9.3895. Min Act: -0.1700
Data Index: 5322726 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3895. Min Range: -9.3895
Max Act: 9.3895. Min Act: -0.1700
Data Index: 8583822 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3895. Min Range: -9.3895
Max Act: 9.3895. Min Act: -0.1700
Data Index: 8180535 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3895. Min Range: -9.3895
Max Act: 9.1395. Min Act: -0.1700
Data Index: 6925857 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3895. Min Range: -9.3895
Max Act: 9.0770. Min Act: -0.1700
Data Index: 4390609 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3895. Min Range: -9.3895
Max Act: 9.0145. Min Act: -0.1700
Data Index: 802235 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.8895. Min Act: -0.1700
Data Index: 4308343 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.8270. Min Act: -0.1700
Data Index: 2792052 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.8895. Min Act: -0.1700
Data Index: 2540020 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.8895. Min Act: -0.1700
Data Index: 5896327 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.8270. Min Act: -0.1700
Data Index: 7146213 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.8270. Min Act: -0.1700
Data Index: 2366719 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.8270. Min Act: -0.1700
Data Index: 4745269 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.8270. Min Act: -0.1700
Data Index: 189046 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.7645. Min Act: -0.1700
Data Index: 7525690 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.7645. Min Act: -0.1700
Data Index: 5911434 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.7645. Min Act: -0.1700
Data Index: 780742 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.7645. Min Act: -0.1700
Data Index: 5799295 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.7645. Min Act: -0.1700
Data Index: 8269011 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3895. Min Range: -9.3895
Max Act: 8.7645. Min Act: -0.1700
Data Index: 102580 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19