Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1864 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.5402. Min Act: -0.1700
Data Index: 551421 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.2590. Min Act: -0.1700
Data Index: 1211818 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.2277. Min Act: -0.1700
Data Index: 5881391 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.1965. Min Act: -0.1700
Data Index: 7625629 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.1652. Min Act: -0.1700
Data Index: 6648297 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.1340. Min Act: -0.1700
Data Index: 8478141 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.1652. Min Act: -0.1700
Data Index: 936323 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.1340. Min Act: -0.1700
Data Index: 593378 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.1340. Min Act: -0.1700
Data Index: 3391039 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.1027. Min Act: -0.1700
Data Index: 2103525 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.0715. Min Act: -0.1700
Data Index: 624549 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.0715. Min Act: -0.1700
Data Index: 7853481 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.0402. Min Act: -0.1700
Data Index: 2237398 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.0402. Min Act: -0.1700
Data Index: 313162 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.0402. Min Act: -0.1700
Data Index: 4720001 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.0090. Min Act: -0.1700
Data Index: 2159441 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.0090. Min Act: -0.1700
Data Index: 1455990 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.0090. Min Act: -0.1700
Data Index: 6521404 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5402. Min Range: -5.5402
Max Act: 4.9777. Min Act: -0.1700
Data Index: 6726433 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5402. Min Range: -5.5402
Max Act: 4.9777. Min Act: -0.1700
Data Index: 6292787 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19