Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 900 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5721. Min Range: -9.5721
Max Act: 9.5721. Min Act: -0.1700
Data Index: 3869910 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5721. Min Range: -9.5721
Max Act: 9.4471. Min Act: -0.1700
Data Index: 516243 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5721. Min Range: -9.5721
Max Act: 9.2596. Min Act: -0.1700
Data Index: 8099410 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5721. Min Range: -9.5721
Max Act: 9.1971. Min Act: -0.1700
Data Index: 7828008 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5721. Min Range: -9.5721
Max Act: 9.1346. Min Act: -0.1700
Data Index: 8429804 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5721. Min Range: -9.5721
Max Act: 9.0721. Min Act: -0.1700
Data Index: 2423392 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5721. Min Range: -9.5721
Max Act: 9.0721. Min Act: -0.1700
Data Index: 6169721 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5721. Min Range: -9.5721
Max Act: 9.0721. Min Act: -0.1700
Data Index: 592276 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5721. Min Range: -9.5721
Max Act: 9.0096. Min Act: -0.1700
Data Index: 7332518 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.9471. Min Act: -0.1700
Data Index: 7037891 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.9471. Min Act: -0.1700
Data Index: 7398152 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.8846. Min Act: -0.1700
Data Index: 6291335 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.9471. Min Act: -0.1700
Data Index: 7285209 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.8846. Min Act: -0.1700
Data Index: 8452730 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.8221. Min Act: -0.1700
Data Index: 6240136 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.8221. Min Act: -0.1700
Data Index: 6670254 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.8221. Min Act: -0.1700
Data Index: 7199847 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.8846. Min Act: -0.1700
Data Index: 2469152 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.7596. Min Act: -0.1700
Data Index: 1277283 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5721. Min Range: -9.5721
Max Act: 8.7596. Min Act: -0.1700
Data Index: 7422139 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19