Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1536 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.7963. Min Act: -0.1700
Data Index: 6314605 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.7650. Min Act: -0.1700
Data Index: 4260458 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.5775. Min Act: -0.1700
Data Index: 397705 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.4838. Min Act: -0.1700
Data Index: 6876859 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.4525. Min Act: -0.1700
Data Index: 7577751 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.4525. Min Act: -0.1700
Data Index: 4698378 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.4213. Min Act: -0.1700
Data Index: 6876868 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.3275. Min Act: -0.1700
Data Index: 7577744 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.3275. Min Act: -0.1700
Data Index: 4209418 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.2963. Min Act: -0.1700
Data Index: 4080409 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.2338. Min Act: -0.1700
Data Index: 1611915 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.2650. Min Act: -0.1700
Data Index: 2283252 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.2338. Min Act: -0.1700
Data Index: 5990056 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.2338. Min Act: -0.1700
Data Index: 1310496 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.2338. Min Act: -0.1700
Data Index: 3663443 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.1400. Min Act: -0.1700
Data Index: 8387062 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.1713. Min Act: -0.1700
Data Index: 8385106 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.1713. Min Act: -0.1700
Data Index: 8385105 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.1713. Min Act: -0.1700
Data Index: 4516745 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7963. Min Range: -6.7963
Max Act: 6.1088. Min Act: -0.1700
Data Index: 4957367 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19