Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.7260. Min Act: -0.1700
Data Index: 6295779 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.6322. Min Act: -0.1700
Data Index: 591033 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.6010. Min Act: -0.1700
Data Index: 2536805 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.5072. Min Act: -0.1700
Data Index: 5689839 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.4760. Min Act: -0.1700
Data Index: 4348394 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.5072. Min Act: -0.1700
Data Index: 526289 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.4447. Min Act: -0.1700
Data Index: 591034 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.4447. Min Act: -0.1700
Data Index: 1387288 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.4135. Min Act: -0.1700
Data Index: 591035 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.3822. Min Act: -0.1700
Data Index: 4525822 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.3822. Min Act: -0.1700
Data Index: 687532 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.3822. Min Act: -0.1700
Data Index: 8753509 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.3822. Min Act: -0.1700
Data Index: 526285 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.3510. Min Act: -0.1700
Data Index: 3251675 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.3822. Min Act: -0.1700
Data Index: 356812 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.2885. Min Act: -0.1700
Data Index: 356813 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.2572. Min Act: -0.1700
Data Index: 2247778 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.2572. Min Act: -0.1700
Data Index: 2600828 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.2260. Min Act: -0.1700
Data Index: 5191504 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7260. Min Range: -6.7260
Max Act: 6.2260. Min Act: -0.1700
Data Index: 3474595 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19