Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4438 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.9447. Min Act: -0.1700
Data Index: 6512864 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.7885. Min Act: -0.1700
Data Index: 6594854 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.6322. Min Act: -0.1700
Data Index: 657718 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.5072. Min Act: -0.1700
Data Index: 5137512 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.4447. Min Act: -0.1700
Data Index: 2395028 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.4135. Min Act: -0.1700
Data Index: 6974577 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.4135. Min Act: -0.1700
Data Index: 2471628 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.4135. Min Act: -0.1700
Data Index: 1927956 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3822. Min Act: -0.1700
Data Index: 325202 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3822. Min Act: -0.1700
Data Index: 7494958 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3822. Min Act: -0.1700
Data Index: 3927557 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3822. Min Act: -0.1700
Data Index: 5591896 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3822. Min Act: -0.1700
Data Index: 5483162 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3510. Min Act: -0.1700
Data Index: 809536 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3510. Min Act: -0.1700
Data Index: 8378223 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3510. Min Act: -0.1700
Data Index: 5516791 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3197. Min Act: -0.1700
Data Index: 7102321 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.2885. Min Act: -0.1700
Data Index: 4344639 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3197. Min Act: -0.1700
Data Index: 2402272 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9447. Min Range: -5.9447
Max Act: 5.3197. Min Act: -0.1700
Data Index: 7388456 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19