Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4519 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1804. Min Range: -7.1804
Max Act: 7.1804. Min Act: -0.1700
Data Index: 5245338 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1804. Min Range: -7.1804
Max Act: 7.0866. Min Act: -0.1700
Data Index: 7534284 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.9929. Min Act: -0.1700
Data Index: 4863883 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1804. Min Range: -7.1804
Max Act: 7.0241. Min Act: -0.1700
Data Index: 3926040 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.9616. Min Act: -0.1700
Data Index: 1477672 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.9616. Min Act: -0.1700
Data Index: 2871024 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.8679. Min Act: -0.1700
Data Index: 7513639 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.8366. Min Act: -0.1700
Data Index: 7060573 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.7741. Min Act: -0.1700
Data Index: 1952356 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.7116. Min Act: -0.1700
Data Index: 5684249 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.7116. Min Act: -0.1700
Data Index: 3242503 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.7116. Min Act: -0.1700
Data Index: 2547649 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.6804. Min Act: -0.1700
Data Index: 2652032 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.6179. Min Act: -0.1700
Data Index: 644161 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.6179. Min Act: -0.1700
Data Index: 7261209 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.5866. Min Act: -0.1700
Data Index: 1134080 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.5554. Min Act: -0.1700
Data Index: 5868244 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.5554. Min Act: -0.1700
Data Index: 7000211 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.5866. Min Act: -0.1700
Data Index: 2699435 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1804. Min Range: -7.1804
Max Act: 6.5554. Min Act: -0.1700
Data Index: 4740341 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19