Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1324 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0773. Min Range: -8.0773
Max Act: 8.0773. Min Act: -0.1700
Data Index: 7807255 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0773. Min Range: -8.0773
Max Act: 8.0148. Min Act: -0.1700
Data Index: 498460 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.9523. Min Act: -0.1700
Data Index: 5460575 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.8898. Min Act: -0.1700
Data Index: 7429188 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.8898. Min Act: -0.1700
Data Index: 8576298 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.8273. Min Act: -0.1700
Data Index: 3353286 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.8273. Min Act: -0.1700
Data Index: 1464717 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.8273. Min Act: -0.1700
Data Index: 5993397 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.7648. Min Act: -0.1700
Data Index: 6736395 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.7648. Min Act: -0.1700
Data Index: 6794164 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.7648. Min Act: -0.1700
Data Index: 259 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.7023. Min Act: -0.1700
Data Index: 268060 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.7023. Min Act: -0.1700
Data Index: 6355740 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.7023. Min Act: -0.1700
Data Index: 1624434 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.7023. Min Act: -0.1700
Data Index: 609190 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.6398. Min Act: -0.1700
Data Index: 8302067 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.7023. Min Act: -0.1700
Data Index: 2541033 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.6398. Min Act: -0.1700
Data Index: 4311020 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.6398. Min Act: -0.1700
Data Index: 3223274 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0773. Min Range: -8.0773
Max Act: 7.6398. Min Act: -0.1700
Data Index: 1066913 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19