Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3377 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.2591. Min Act: -0.1700
Data Index: 4907039 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1966. Min Act: -0.1700
Data Index: 5088027 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.2591. Min Act: -0.1700
Data Index: 6501731 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1654. Min Act: -0.1700
Data Index: 6100512 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1966. Min Act: -0.1700
Data Index: 470146 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1966. Min Act: -0.1700
Data Index: 6423284 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1654. Min Act: -0.1700
Data Index: 6058913 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1654. Min Act: -0.1700
Data Index: 340079 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1341. Min Act: -0.1700
Data Index: 2295141 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1341. Min Act: -0.1700
Data Index: 1054737 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1341. Min Act: -0.1700
Data Index: 7253518 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1029. Min Act: -0.1700
Data Index: 5844225 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.1029. Min Act: -0.1700
Data Index: 8488264 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.0716. Min Act: -0.1700
Data Index: 4714994 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.0716. Min Act: -0.1700
Data Index: 6180638 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.0404. Min Act: -0.1700
Data Index: 3846578 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.0404. Min Act: -0.1700
Data Index: 637437 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.0716. Min Act: -0.1700
Data Index: 2723590 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.0404. Min Act: -0.1700
Data Index: 2377670 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2591. Min Range: -6.2591
Max Act: 6.0091. Min Act: -0.1700
Data Index: 3913510 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19