Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.6387. Min Act: -0.1700
Data Index: 2661711 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.5762. Min Act: -0.1700
Data Index: 8184841 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.5137. Min Act: -0.1700
Data Index: 3478993 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.4199. Min Act: -0.1700
Data Index: 3697400 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.3574. Min Act: -0.1700
Data Index: 7768828 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.3262. Min Act: -0.1700
Data Index: 3306792 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.2324. Min Act: -0.1700
Data Index: 3900224 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.2324. Min Act: -0.1700
Data Index: 3807951 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.2324. Min Act: -0.1700
Data Index: 6492149 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.2324. Min Act: -0.1700
Data Index: 75675 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.2012. Min Act: -0.1700
Data Index: 1148703 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.1699. Min Act: -0.1700
Data Index: 7783007 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.1699. Min Act: -0.1700
Data Index: 5745349 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.1074. Min Act: -0.1700
Data Index: 4263972 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.1074. Min Act: -0.1700
Data Index: 2928522 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.1387. Min Act: -0.1700
Data Index: 7322796 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.0762. Min Act: -0.1700
Data Index: 8268617 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.0449. Min Act: -0.1700
Data Index: 3662435 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.0449. Min Act: -0.1700
Data Index: 2902792 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6387. Min Range: -7.6387
Max Act: 7.0449. Min Act: -0.1700
Data Index: 7101317 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19